diff --git a/configs/cascade_mask_rcnn_r101_fpn_1x.py b/configs/cascade_mask_rcnn_r101_fpn_1x.py
index 1b63d2b2703f83f94b1a3cb30d86ca228582b6ce..0ad9c88207b061ed6be72a35fb4687081fc72934 100644
--- a/configs/cascade_mask_rcnn_r101_fpn_1x.py
+++ b/configs/cascade_mask_rcnn_r101_fpn_1x.py
@@ -44,13 +44,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -62,13 +57,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -80,13 +70,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -196,6 +181,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -203,35 +213,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_mask_rcnn_r50_caffe_c4_1x.py b/configs/cascade_mask_rcnn_r50_caffe_c4_1x.py
index cdf5ff03650848bcd19199cdb57ec26421a264db..dd5f356b4df35256b4ae9e0a1911907667cb4633 100644
--- a/configs/cascade_mask_rcnn_r50_caffe_c4_1x.py
+++ b/configs/cascade_mask_rcnn_r50_caffe_c4_1x.py
@@ -52,13 +52,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='BBoxHead',
with_avg_pool=True,
@@ -69,13 +64,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='BBoxHead',
with_avg_pool=True,
@@ -86,13 +76,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=None,
mask_head=dict(
@@ -198,42 +183,49 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
- imgs_per_gpu=1,
+ imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_mask_rcnn_r50_fpn_1x.py b/configs/cascade_mask_rcnn_r50_fpn_1x.py
index 39450b812b4f8d8420c3161c03b506626d044174..c9f007ed653b76b09d9e680143a5fa9bb5261af4 100644
--- a/configs/cascade_mask_rcnn_r50_fpn_1x.py
+++ b/configs/cascade_mask_rcnn_r50_fpn_1x.py
@@ -44,13 +44,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -62,13 +57,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -80,13 +70,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -196,6 +181,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -203,35 +213,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_mask_rcnn_x101_32x4d_fpn_1x.py b/configs/cascade_mask_rcnn_x101_32x4d_fpn_1x.py
index e8a31d0549e54d6d5ff7f390ac8b2bf4c5897a5b..3167be4c340c5feddf09fce9984a09542ae9370d 100644
--- a/configs/cascade_mask_rcnn_x101_32x4d_fpn_1x.py
+++ b/configs/cascade_mask_rcnn_x101_32x4d_fpn_1x.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -198,6 +183,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -205,35 +215,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_mask_rcnn_x101_64x4d_fpn_1x.py b/configs/cascade_mask_rcnn_x101_64x4d_fpn_1x.py
index 1661a105201c77c128623b8579db3aa3181a189b..0c5434ead4d6df865180cf4edb0b45c73b54cb5f 100644
--- a/configs/cascade_mask_rcnn_x101_64x4d_fpn_1x.py
+++ b/configs/cascade_mask_rcnn_x101_64x4d_fpn_1x.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -198,6 +183,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -205,35 +215,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_rcnn_r101_fpn_1x.py b/configs/cascade_rcnn_r101_fpn_1x.py
index a09131404a30b0f59a09002c3de179660d35100c..a790c2bd55bf9e0b7205876d6805b909de75f6a3 100644
--- a/configs/cascade_rcnn_r101_fpn_1x.py
+++ b/configs/cascade_rcnn_r101_fpn_1x.py
@@ -44,13 +44,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -62,13 +57,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -80,13 +70,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
])
# model training and testing settings
train_cfg = dict(
@@ -177,6 +162,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -184,35 +194,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_rcnn_r50_caffe_c4_1x.py b/configs/cascade_rcnn_r50_caffe_c4_1x.py
index 978724b9d428be44bea6f8a92a002ad706757d94..0dd10abb00b993e8e51c51d92780ae914f05dd08 100644
--- a/configs/cascade_rcnn_r50_caffe_c4_1x.py
+++ b/configs/cascade_rcnn_r50_caffe_c4_1x.py
@@ -52,13 +52,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='BBoxHead',
with_avg_pool=True,
@@ -69,13 +64,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='BBoxHead',
with_avg_pool=True,
@@ -86,13 +76,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
])
# model training and testing settings
train_cfg = dict(
@@ -186,42 +171,49 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
- imgs_per_gpu=1,
+ imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_rcnn_r50_fpn_1x.py b/configs/cascade_rcnn_r50_fpn_1x.py
index 045f0eb28d9ac53c2f20ae3fe665897bdbfcbd5e..96269fab0051dcf6ca591b305f18d1bf7ed2e090 100644
--- a/configs/cascade_rcnn_r50_fpn_1x.py
+++ b/configs/cascade_rcnn_r50_fpn_1x.py
@@ -44,13 +44,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -62,13 +57,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -80,13 +70,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
])
# model training and testing settings
train_cfg = dict(
@@ -177,6 +162,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -184,35 +194,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_rcnn_x101_32x4d_fpn_1x.py b/configs/cascade_rcnn_x101_32x4d_fpn_1x.py
index 7ce7aab875fbd08a6eb700aeb786ecb8bce50456..6de3d37d7177423e7347a7c62aa2c5d1b80e8b36 100644
--- a/configs/cascade_rcnn_x101_32x4d_fpn_1x.py
+++ b/configs/cascade_rcnn_x101_32x4d_fpn_1x.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
])
# model training and testing settings
train_cfg = dict(
@@ -179,6 +164,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -186,35 +196,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cascade_rcnn_x101_64x4d_fpn_1x.py b/configs/cascade_rcnn_x101_64x4d_fpn_1x.py
index 401dfac8ca17dc1f08eb92fc7d561d623374e36a..d6e9d1f6f12dc0c8583d1d997703c2a94b6ae369 100644
--- a/configs/cascade_rcnn_x101_64x4d_fpn_1x.py
+++ b/configs/cascade_rcnn_x101_64x4d_fpn_1x.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
])
# model training and testing settings
train_cfg = dict(
@@ -179,6 +164,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -186,35 +196,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py b/configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py
index 0ccacd201fffe1343adca24b87270dfa228186cd..2f2c03556275ea88f6230ff5dc52474c5ce75127 100644
--- a/configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py
+++ b/configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py
@@ -102,49 +102,56 @@ dataset_type = 'CityscapesDataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(2048, 1024),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=1,
workers_per_gpu=2,
train=dict(
- type='RepeatDataset', # to avoid reloading datasets frequently
+ type='RepeatDataset',
times=8,
dataset=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_train.json',
img_prefix=data_root + 'train/',
- img_scale=[(2048, 800), (2048, 1024)],
- img_norm_cfg=img_norm_cfg,
- multiscale_mode='range',
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True)),
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
- img_scale=(2048, 1024),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
- img_scale=(2048, 1024),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
# lr is set for a batch size of 8
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
diff --git a/configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py b/configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py
index 85f32f7e809a76ea72690cd4763bcc9ababd2f91..84082506674c5f16f1c6a040095e89abf34e4e69 100644
--- a/configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py
+++ b/configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py
@@ -116,49 +116,56 @@ dataset_type = 'CityscapesDataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(
+ type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(2048, 1024),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=1,
workers_per_gpu=2,
train=dict(
- type='RepeatDataset', # to avoid reloading datasets frequently
+ type='RepeatDataset',
times=8,
dataset=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_train.json',
img_prefix=data_root + 'train/',
- img_scale=[(2048, 800), (2048, 1024)],
- img_norm_cfg=img_norm_cfg,
- multiscale_mode='range',
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True)),
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
- img_scale=(2048, 1024),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
- img_scale=(2048, 1024),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
# lr is set for a batch size of 8
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
diff --git a/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
index 2865922a86e930d275f23e43f112f386667d5221..27476d3a9a0434f5a458e8f15eb7cb833fa742cf 100644
--- a/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -184,6 +184,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -191,35 +216,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py
index d3ea852f391b45315a12965b3e787b0a14ea5f29..9f9f10cf0ad7318ca7edebd9994a90ed43ff424f 100644
--- a/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -11,9 +11,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
- modulated=False,
- deformable_groups=1,
- fallback_on_stride=False),
+ modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
@@ -49,13 +47,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -67,13 +60,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -85,13 +73,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
])
# model training and testing settings
train_cfg = dict(
@@ -182,6 +165,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -189,35 +197,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py
index 0f028991acf18aaaed5ff9bf07b0efbec310e97e..11c7dd35e6aee4503de4e4bacb8013434dad8c6f 100644
--- a/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -105,6 +105,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -112,35 +137,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/dcn/faster_rcnn_dconv_c3-c5_x101_32x4d_fpn_1x.py b/configs/dcn/faster_rcnn_dconv_c3-c5_x101_32x4d_fpn_1x.py
index 31aa1981700a23080098be8e0e31849a88f79862..9156b0d8ba6f509c593b6ce4613c2566cb958a93 100644
--- a/configs/dcn/faster_rcnn_dconv_c3-c5_x101_32x4d_fpn_1x.py
+++ b/configs/dcn/faster_rcnn_dconv_c3-c5_x101_32x4d_fpn_1x.py
@@ -110,6 +110,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -117,35 +142,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/dcn/faster_rcnn_dpool_r50_fpn_1x.py b/configs/dcn/faster_rcnn_dpool_r50_fpn_1x.py
index ec3872205fc1dcfcc15b0a4074f36afdd8516cb4..bddcce40cd2cee9f9f9a7ebee34e464cb69f3e01 100644
--- a/configs/dcn/faster_rcnn_dpool_r50_fpn_1x.py
+++ b/configs/dcn/faster_rcnn_dpool_r50_fpn_1x.py
@@ -108,6 +108,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -115,35 +140,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py b/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py
index 1aca07ed27ee6b55d08207ecbf4879a284001646..484b4aff10782debbace72a218bf538f9785fefd 100644
--- a/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py
@@ -105,6 +105,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -112,35 +137,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/dcn/faster_rcnn_mdpool_r50_fpn_1x.py b/configs/dcn/faster_rcnn_mdpool_r50_fpn_1x.py
index bb8d3c4d26d2ca5303ddc50698ec254c72122f27..fba0b330bfeefd55f3824658dc2f8b777e98edb3 100644
--- a/configs/dcn/faster_rcnn_mdpool_r50_fpn_1x.py
+++ b/configs/dcn/faster_rcnn_mdpool_r50_fpn_1x.py
@@ -108,6 +108,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -115,35 +140,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
index 6f910aa22f4ab03d669816287ec19d01db1e729e..c3de699a1c4aff0551830aa4e034edddeb15fd84 100644
--- a/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -10,9 +10,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
- modulated=False,
- deformable_groups=1,
- fallback_on_stride=False),
+ modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
@@ -121,6 +119,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -128,35 +151,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/double_heads/dh_faster_rcnn_r50_fpn_1x.py b/configs/double_heads/dh_faster_rcnn_r50_fpn_1x.py
index cef46570279d5835ddad67b2569ecc5ec8ccfad4..708f67265b8f124f8df67cca06c93d4e7f311237 100644
--- a/configs/double_heads/dh_faster_rcnn_r50_fpn_1x.py
+++ b/configs/double_heads/dh_faster_rcnn_r50_fpn_1x.py
@@ -105,6 +105,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -112,35 +137,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x.py b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x.py
index 4adba5d485737d840fa9edb58799587020dcd20c..db20d8d2c979f91b25dfe82398df852d716ea3cc 100644
--- a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x.py
+++ b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x.py
@@ -106,6 +106,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -113,35 +138,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x.py b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x.py
index f8e1f83a15937d59d7fe5cbb114e6caaa8663878..d264b9bf4ad1f18c533ea7fe35b4ef27117a95e8 100644
--- a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x.py
+++ b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x.py
@@ -109,6 +109,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -116,35 +141,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x.py b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x.py
index 4a43cced746ae66dd35915a3544d7d830b0365cf..f3eace271f576641de1fb35e7e6ebaf90a363e39 100644
--- a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x.py
+++ b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x.py
@@ -106,6 +106,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -113,35 +138,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x.py b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x.py
index 0a3cf0e27af94614366ca6fadc22319b70965976..f39edee846eaeb5e886f06b88141da7d96e17ed0 100644
--- a/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x.py
+++ b/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x.py
@@ -109,6 +109,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -116,35 +141,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fast_mask_rcnn_r101_fpn_1x.py b/configs/fast_mask_rcnn_r101_fpn_1x.py
index 0a9fc45e3a3d7a2e25ada472bf5f8e6320d859e2..576d488a1ca761836c7a651faacd34903d398e02 100644
--- a/configs/fast_mask_rcnn_r101_fpn_1x.py
+++ b/configs/fast_mask_rcnn_r101_fpn_1x.py
@@ -74,45 +74,56 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=2000),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'proposals', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fast_mask_rcnn_r50_caffe_c4_1x.py b/configs/fast_mask_rcnn_r50_caffe_c4_1x.py
index 1aa97e054a6a2d57b033031605535762afa18db8..cca87107861308fbeb0ade85eb1f9ee206083add 100644
--- a/configs/fast_mask_rcnn_r50_caffe_c4_1x.py
+++ b/configs/fast_mask_rcnn_r50_caffe_c4_1x.py
@@ -73,45 +73,56 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=2000),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'proposals', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
- imgs_per_gpu=1,
+ imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_c4_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fast_mask_rcnn_r50_fpn_1x.py b/configs/fast_mask_rcnn_r50_fpn_1x.py
index 81a46e64acb6faf0132205f526fc1c11d26f4db2..c324356d5a2ffff2e0b3d3884b50478569cf85b9 100644
--- a/configs/fast_mask_rcnn_r50_fpn_1x.py
+++ b/configs/fast_mask_rcnn_r50_fpn_1x.py
@@ -74,45 +74,56 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=2000),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'proposals', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fast_rcnn_r101_fpn_1x.py b/configs/fast_rcnn_r101_fpn_1x.py
index 51cca7a18230e04f8245faa2285460469906ad46..06d88126a1d6b0c9834654da6b571fffbebce3a7 100644
--- a/configs/fast_rcnn_r101_fpn_1x.py
+++ b/configs/fast_rcnn_r101_fpn_1x.py
@@ -30,11 +30,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rcnn=dict(
@@ -60,45 +57,54 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=2000),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fast_rcnn_r50_caffe_c4_1x.py b/configs/fast_rcnn_r50_caffe_c4_1x.py
index 5d78bafb7b018d5ac001fb41f5d4cacd2c18837c..d1c6f3ab56438876f4a5f79c1f6dde8b8d9de62e 100644
--- a/configs/fast_rcnn_r50_caffe_c4_1x.py
+++ b/configs/fast_rcnn_r50_caffe_c4_1x.py
@@ -38,11 +38,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rcnn=dict(
@@ -68,45 +65,54 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=2000),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
- imgs_per_gpu=1,
+ imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_c4_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fast_rcnn_r50_fpn_1x.py b/configs/fast_rcnn_r50_fpn_1x.py
index 8d58453df0fec69751732683742364b156e71e75..b22dede05d9a1fba1ba433985c20ea192f4c9ca0 100644
--- a/configs/fast_rcnn_r50_fpn_1x.py
+++ b/configs/fast_rcnn_r50_fpn_1x.py
@@ -30,11 +30,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rcnn=dict(
@@ -60,45 +57,54 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=2000),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/faster_rcnn_ohem_r50_fpn_1x.py b/configs/faster_rcnn_ohem_r50_fpn_1x.py
index 9e65c106b3df627f9b89325ffe5c426569ab46c5..e2dbc8df9918818b19164c157ca2142f110a8375 100644
--- a/configs/faster_rcnn_ohem_r50_fpn_1x.py
+++ b/configs/faster_rcnn_ohem_r50_fpn_1x.py
@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -109,35 +134,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/faster_rcnn_r101_fpn_1x.py b/configs/faster_rcnn_r101_fpn_1x.py
index f77028ec1f7880e05cbd6a26f758129a913b7290..e0ad7066f48d4e521bbce5b00d3f6d0a1841336c 100644
--- a/configs/faster_rcnn_r101_fpn_1x.py
+++ b/configs/faster_rcnn_r101_fpn_1x.py
@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -109,35 +134,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/faster_rcnn_r50_caffe_c4_1x.py b/configs/faster_rcnn_r50_caffe_c4_1x.py
index ebbcc4e0cb780ce0ecc30686f80e87bf87a514a1..ddd8113420a87555c496a564b3547253fee5f8ef 100644
--- a/configs/faster_rcnn_r50_caffe_c4_1x.py
+++ b/configs/faster_rcnn_r50_caffe_c4_1x.py
@@ -107,42 +107,49 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
- imgs_per_gpu=1,
+ imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/faster_rcnn_r50_fpn_1x.py b/configs/faster_rcnn_r50_fpn_1x.py
index a6049cd6012a4ad086982c703b7530205e3e3955..0c5e243ac2aeb8b222ccf45e73aa38853721f122 100644
--- a/configs/faster_rcnn_r50_fpn_1x.py
+++ b/configs/faster_rcnn_r50_fpn_1x.py
@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -109,35 +134,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/faster_rcnn_x101_32x4d_fpn_1x.py b/configs/faster_rcnn_x101_32x4d_fpn_1x.py
index 50b479d0e0575ef9267874def8e62e09345bfd6b..8f3c6f706f4dcd134587990670ab1fc99a7a2862 100644
--- a/configs/faster_rcnn_x101_32x4d_fpn_1x.py
+++ b/configs/faster_rcnn_x101_32x4d_fpn_1x.py
@@ -104,6 +104,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -111,35 +136,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/faster_rcnn_x101_64x4d_fpn_1x.py b/configs/faster_rcnn_x101_64x4d_fpn_1x.py
index 4397d2defd16524dee102ba3d479f7bdcf94b7c2..90ad0ac3a998e949abe0ec27b80dea3269f4a09a 100644
--- a/configs/faster_rcnn_x101_64x4d_fpn_1x.py
+++ b/configs/faster_rcnn_x101_64x4d_fpn_1x.py
@@ -104,6 +104,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -111,35 +136,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu.py b/configs/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu.py
index ac21fada1667ec4c8dc7153798ec8d01f02b1dc3..0356a5730e428e5c6a58c0c120a7e0a05fad9b54 100644
--- a/configs/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu.py
+++ b/configs/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu.py
@@ -57,6 +57,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='Resize',
+ img_scale=[(1333, 640), (1333, 800)],
+ multiscale_mode='value',
+ keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=4,
workers_per_gpu=4,
@@ -64,37 +93,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=[(1333, 640), (1333, 800)],
- multiscale_mode='value',
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
diff --git a/configs/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x.py b/configs/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x.py
index d932bcfe2aabfa0c0808f2fe867b2981ae2677b4..c6f725a75ddbaa406e63b4be54440b1e9cbcb78b 100644
--- a/configs/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x.py
+++ b/configs/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x.py
@@ -58,6 +58,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='Resize',
+ img_scale=[(1333, 640), (1333, 800)],
+ multiscale_mode='value',
+ keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -65,37 +94,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=[(1333, 640), (1333, 800)],
- multiscale_mode='value',
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
diff --git a/configs/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu.py b/configs/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu.py
index 6243c3645909bfe377525f4e4417538eae80f0dd..2c3248ae1be28534e1b8ad7eeea4a386b9358aad 100644
--- a/configs/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu.py
+++ b/configs/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu.py
@@ -57,6 +57,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=4,
workers_per_gpu=4,
@@ -64,36 +89,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
diff --git a/configs/fp16/faster_rcnn_r50_fpn_fp16_1x.py b/configs/fp16/faster_rcnn_r50_fpn_fp16_1x.py
index 161a9756cfd060aebe7882a5df5b9168ee2687f5..20ff20b4b966e738c783a5afe1bc8d2f6d25e061 100644
--- a/configs/fp16/faster_rcnn_r50_fpn_fp16_1x.py
+++ b/configs/fp16/faster_rcnn_r50_fpn_fp16_1x.py
@@ -105,6 +105,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -112,35 +137,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fp16/mask_rcnn_r50_fpn_fp16_1x.py b/configs/fp16/mask_rcnn_r50_fpn_fp16_1x.py
index 31b32f080777c9f2e16d1ad299bf5acd60a4166f..23cbcf5267a44be55815ac680a5f06b48ef98d3e 100644
--- a/configs/fp16/mask_rcnn_r50_fpn_fp16_1x.py
+++ b/configs/fp16/mask_rcnn_r50_fpn_fp16_1x.py
@@ -119,6 +119,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -126,35 +151,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/fp16/retinanet_r50_fpn_fp16_1x.py b/configs/fp16/retinanet_r50_fpn_fp16_1x.py
index 87432f7ccbe3d3d882c2fb884a6bf6f8b5387dc3..a0577e770dd145f59042b005451471f313181970 100644
--- a/configs/fp16/retinanet_r50_fpn_fp16_1x.py
+++ b/configs/fp16/retinanet_r50_fpn_fp16_1x.py
@@ -60,6 +60,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -67,36 +92,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_1x.py b/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_1x.py
index 480e40337d5709fad197c00d3b3eaa68b6cb52ce..bc949074c831057dbde277b5b992d44daaceb824 100644
--- a/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_1x.py
+++ b/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_1x.py
@@ -9,9 +9,7 @@ model = dict(
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
- gcb=dict(
- ratio=1./16.,
- ),
+ gcb=dict(ratio=1. / 16., ),
stage_with_gcb=(False, True, True, True)),
neck=dict(
type='FPN',
@@ -120,6 +118,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -127,35 +150,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_syncbn_1x.py b/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_syncbn_1x.py
index 349a52acca448dfdc494ed0d76c7397608c5cf16..ad06c9b84a8d308c16709bcc6aac510949cefbc1 100644
--- a/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_syncbn_1x.py
+++ b/configs/gcnet/mask_rcnn_r16_gcb_c3-c5_r50_fpn_syncbn_1x.py
@@ -11,9 +11,7 @@ model = dict(
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
- gcb=dict(
- ratio=1./16.,
- ),
+ gcb=dict(ratio=1. / 16., ),
stage_with_gcb=(False, True, True, True),
norm_eval=False,
norm_cfg=norm_cfg),
@@ -124,6 +122,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -131,35 +154,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_1x.py b/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_1x.py
index 08b26055a4320bd321dcc37860ed8422b54bdba2..5568b2f7987f79460b817f52b2298463268dfc64 100644
--- a/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_1x.py
+++ b/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_1x.py
@@ -9,9 +9,7 @@ model = dict(
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
- gcb=dict(
- ratio=1./4.,
- ),
+ gcb=dict(ratio=1. / 4., ),
stage_with_gcb=(False, True, True, True)),
neck=dict(
type='FPN',
@@ -120,6 +118,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -127,35 +150,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_syncbn_1x.py b/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_syncbn_1x.py
index b8b55647eac65565834922bf4dee6c55ac7baff4..6a32126ec785724516a9a9d99b9f69ecc8ba6dfa 100644
--- a/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_syncbn_1x.py
+++ b/configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_syncbn_1x.py
@@ -11,9 +11,7 @@ model = dict(
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
- gcb=dict(
- ratio=1./4.,
- ),
+ gcb=dict(ratio=1. / 4., ),
stage_with_gcb=(False, True, True, True),
norm_eval=False,
norm_cfg=norm_cfg),
@@ -124,6 +122,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -131,35 +154,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gcnet/mask_rcnn_r50_fpn_sbn_1x.py b/configs/gcnet/mask_rcnn_r50_fpn_sbn_1x.py
index b261934b66dea19335cc938f601fd3792b179fc3..819c78facd935fb62d0a01c92e8076598cf3933e 100644
--- a/configs/gcnet/mask_rcnn_r50_fpn_sbn_1x.py
+++ b/configs/gcnet/mask_rcnn_r50_fpn_sbn_1x.py
@@ -120,6 +120,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -127,35 +152,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/ghm/retinanet_ghm_r50_fpn_1x.py b/configs/ghm/retinanet_ghm_r50_fpn_1x.py
index eddf36846e1f505113ea44dbeb8f1bbea28cdae9..ea90fb7d78af86548f94cc76d5bfa5dd72c7083e 100644
--- a/configs/ghm/retinanet_ghm_r50_fpn_1x.py
+++ b/configs/ghm/retinanet_ghm_r50_fpn_1x.py
@@ -35,11 +35,7 @@ model = dict(
use_sigmoid=True,
loss_weight=1.0),
loss_bbox=dict(
- type='GHMR',
- mu=0.02,
- bins=10,
- momentum=0.7,
- loss_weight=10.0)))
+ type='GHMR', mu=0.02, bins=10, momentum=0.7, loss_weight=10.0)))
# training and testing settings
train_cfg = dict(
assigner=dict(
@@ -62,6 +58,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -69,36 +90,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py b/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py
index 0eef1e9d55c1ccf20235c48449d8307ddd480eed..eef21dbf7e482eaee7a6b2a82d92dd2adb5e2ab9 100644
--- a/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py
+++ b/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py
@@ -109,6 +109,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -116,35 +141,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_20_23_24e.py b/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_20_23_24e.py
index da39db1b4e41b9af0227ab1f3c2f4a7d6f0da85c..8856c84ec27c03f29bef219bca7812b6e3be7d88 100644
--- a/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_20_23_24e.py
+++ b/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_20_23_24e.py
@@ -128,6 +128,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -135,35 +160,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_2x.py b/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_2x.py
index c023ec3aae1f2e7f2ccb5b2a3d6b963b652fcb69..ce0348ff8ff0f7bf086e227ec81728623f46b5c4 100644
--- a/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_2x.py
+++ b/configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_2x.py
@@ -128,6 +128,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -135,35 +160,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws_2x.py b/configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws_2x.py
index 271ed6e4c8f7bcbcee26e0ec32581de8437773f7..b250590d94af082702ddfb4284f4d11e3700eb57 100644
--- a/configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws_2x.py
+++ b/configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws_2x.py
@@ -130,6 +130,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -137,35 +162,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gn/mask_rcnn_r101_fpn_gn_2x.py b/configs/gn/mask_rcnn_r101_fpn_gn_2x.py
index ae09042d07032d6cc4977cf2e0f55ab17b1a7a23..ae1aeb89d3e6bd70e1ef5ef50a32182911480763 100644
--- a/configs/gn/mask_rcnn_r101_fpn_gn_2x.py
+++ b/configs/gn/mask_rcnn_r101_fpn_gn_2x.py
@@ -124,6 +124,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -131,35 +156,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gn/mask_rcnn_r50_fpn_gn_2x.py b/configs/gn/mask_rcnn_r50_fpn_gn_2x.py
index bbeaa78f6dbc34798a8d47392aeaa9738b1ad538..43ecf9ea9f1d1f48a22316b0fbcaba5fb103ba7c 100644
--- a/configs/gn/mask_rcnn_r50_fpn_gn_2x.py
+++ b/configs/gn/mask_rcnn_r50_fpn_gn_2x.py
@@ -124,6 +124,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -131,35 +156,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py b/configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py
index 87db0f5447374caca51977b9ddee017d43728e68..ee4ffafdc0a80f1a2de4f6a8b4e24adbf217fe90 100644
--- a/configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py
+++ b/configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py
@@ -124,6 +124,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -131,35 +156,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/grid_rcnn/grid_rcnn_gn_head_r50_fpn_2x.py b/configs/grid_rcnn/grid_rcnn_gn_head_r50_fpn_2x.py
index cbe345179e9321f066ff248842e18bbde4962045..5a2c071f70d224cf112c6f7846257ecb441f3630 100644
--- a/configs/grid_rcnn/grid_rcnn_gn_head_r50_fpn_2x.py
+++ b/configs/grid_rcnn/grid_rcnn_gn_head_r50_fpn_2x.py
@@ -113,6 +113,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -120,35 +145,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
diff --git a/configs/grid_rcnn/grid_rcnn_gn_head_x101_32x4d_fpn_2x.py b/configs/grid_rcnn/grid_rcnn_gn_head_x101_32x4d_fpn_2x.py
index b08f8095c7b3bf048c0c4955ed327eef67123787..989065ec7bb1f4e090a891bced85aaa6eb7544db 100644
--- a/configs/grid_rcnn/grid_rcnn_gn_head_x101_32x4d_fpn_2x.py
+++ b/configs/grid_rcnn/grid_rcnn_gn_head_x101_32x4d_fpn_2x.py
@@ -115,6 +115,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -122,35 +147,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
diff --git a/configs/guided_anchoring/ga_fast_r50_caffe_fpn_1x.py b/configs/guided_anchoring/ga_fast_r50_caffe_fpn_1x.py
index 269967df0ad43c25b4cec783c8db86860d4da7bb..98fabd29ccb9042ba85f18db379d883a09e04f83 100644
--- a/configs/guided_anchoring/ga_fast_r50_caffe_fpn_1x.py
+++ b/configs/guided_anchoring/ga_fast_r50_caffe_fpn_1x.py
@@ -59,48 +59,54 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=300),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- num_max_proposals=300,
proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- num_max_proposals=300,
proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_val2017.pkl',
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- num_max_proposals=300,
proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_val2017.pkl',
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/guided_anchoring/ga_faster_r50_caffe_fpn_1x.py b/configs/guided_anchoring/ga_faster_r50_caffe_fpn_1x.py
index f78e1c1812ebf8843490aaeb05db68bcf464fda4..791368cd750f30a9cabab5cb542a5f370bbad073 100644
--- a/configs/guided_anchoring/ga_faster_r50_caffe_fpn_1x.py
+++ b/configs/guided_anchoring/ga_faster_r50_caffe_fpn_1x.py
@@ -127,6 +127,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -134,35 +159,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/guided_anchoring/ga_faster_x101_32x4d_fpn_1x.py b/configs/guided_anchoring/ga_faster_x101_32x4d_fpn_1x.py
index 61e7b99e667822bf5fd9be46152febd907d220fb..b0f2cb3b9bfc306fc05f58bf9077b42a2080cb7d 100644
--- a/configs/guided_anchoring/ga_faster_x101_32x4d_fpn_1x.py
+++ b/configs/guided_anchoring/ga_faster_x101_32x4d_fpn_1x.py
@@ -127,6 +127,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -134,35 +159,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x.py b/configs/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x.py
index ae6a18a9d452709ac3d700ed1c956e66fdc82828..175b964f080954c0ac7b252be49c9864111ee668 100644
--- a/configs/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x.py
+++ b/configs/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x.py
@@ -84,6 +84,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -91,36 +116,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x.py b/configs/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x.py
index 32f2bd620c044b61fe186e04cd9184478bf312c3..7bc348409a4ce65fbe196e2bc1a74fbe27e24517 100644
--- a/configs/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x.py
+++ b/configs/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x.py
@@ -84,6 +84,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -91,36 +116,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/guided_anchoring/ga_rpn_r101_caffe_rpn_1x.py b/configs/guided_anchoring/ga_rpn_r101_caffe_rpn_1x.py
index c3d3b65654c08451708fb882f5b259bbca6b2802..8d81f326d8253e34e6e41514615555ed9f56459b 100644
--- a/configs/guided_anchoring/ga_rpn_r101_caffe_rpn_1x.py
+++ b/configs/guided_anchoring/ga_rpn_r101_caffe_rpn_1x.py
@@ -85,6 +85,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -92,35 +117,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/guided_anchoring/ga_rpn_r50_caffe_fpn_1x.py b/configs/guided_anchoring/ga_rpn_r50_caffe_fpn_1x.py
index a4b6b6d624c663ce1b662e87440e5d9fa002c668..9d6b7cebbb6dec4069d949a5ccc01acee3ca33b0 100644
--- a/configs/guided_anchoring/ga_rpn_r50_caffe_fpn_1x.py
+++ b/configs/guided_anchoring/ga_rpn_r50_caffe_fpn_1x.py
@@ -85,6 +85,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -92,35 +117,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x.py b/configs/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x.py
index 9eb1a69cc648388b0723dc1c33cb4380d3c4bc0f..1c5b7a0f89bdc9aab8b0e8cc690a6d7abb7dc26c 100644
--- a/configs/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x.py
+++ b/configs/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x.py
@@ -85,6 +85,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -92,35 +117,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e.py b/configs/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e.py
index 06e0c169ac56de0cead56c9570b41374250f8e7c..17fe9455bb2c8735db2d5aa24f9aae05e4cd1b4b 100644
--- a/configs/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e.py
+++ b/configs/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e.py
@@ -30,10 +30,7 @@ model = dict(
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(32, 64, 128, 256)))),
- neck=dict(
- type='HRFPN',
- in_channels=[32, 64, 128, 256],
- out_channels=256),
+ neck=dict(type='HRFPN', in_channels=[32, 64, 128, 256], out_channels=256),
rpn_head=dict(
type='RPNHead',
in_channels=256,
@@ -63,13 +60,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -81,13 +73,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -99,13 +86,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -215,6 +197,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -222,35 +229,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/hrnet/cascade_rcnn_hrnetv2p_w32_20e.py b/configs/hrnet/cascade_rcnn_hrnetv2p_w32_20e.py
index 512c652451940c2366b71d31b5ec547e58dbb2c6..65eedd15a575aa803d21cd083b3fdf42dee239f0 100644
--- a/configs/hrnet/cascade_rcnn_hrnetv2p_w32_20e.py
+++ b/configs/hrnet/cascade_rcnn_hrnetv2p_w32_20e.py
@@ -30,10 +30,7 @@ model = dict(
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(32, 64, 128, 256)))),
- neck=dict(
- type='HRFPN',
- in_channels=[32, 64, 128, 256],
- out_channels=256),
+ neck=dict(type='HRFPN', in_channels=[32, 64, 128, 256], out_channels=256),
rpn_head=dict(
type='RPNHead',
in_channels=256,
@@ -48,10 +45,7 @@ model = dict(
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
- roi_layer=dict(
- type='RoIAlign',
- out_size=7,
- sample_num=2),
+ roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
@@ -66,13 +60,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -84,13 +73,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -102,13 +86,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
])
# model training and testing settings
train_cfg = dict(
@@ -192,17 +171,38 @@ test_cfg = dict(
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
- score_thr=0.05,
- nms=dict(type='nms', iou_thr=0.5),
- max_per_img=100),
+ score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100),
keep_all_stages=False)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- to_rgb=True)
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -210,35 +210,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x.py b/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x.py
index ceada23d245e1c98cf5ca1c39f63aa4b8ff503bd..f3a298f5faf5030803bca552a45b392676104ad5 100644
--- a/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x.py
+++ b/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x.py
@@ -119,44 +119,51 @@ test_cfg = dict(
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
-img_norm_cfg = dict(mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375], to_rgb=True)
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
- workers_per_gpu=4,
+ workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/hrnet/faster_rcnn_hrnetv2p_w32_1x.py b/configs/hrnet/faster_rcnn_hrnetv2p_w32_1x.py
index 41dfade169f663b26a608d98b592cee87daac6a5..72ad914557aaadd8e5c588f9f0c25ed1652eb256 100644
--- a/configs/hrnet/faster_rcnn_hrnetv2p_w32_1x.py
+++ b/configs/hrnet/faster_rcnn_hrnetv2p_w32_1x.py
@@ -119,8 +119,33 @@ test_cfg = dict(
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
-img_norm_cfg = dict(mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375], to_rgb=True)
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -128,35 +153,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/hrnet/faster_rcnn_hrnetv2p_w40_1x.py b/configs/hrnet/faster_rcnn_hrnetv2p_w40_1x.py
index 72d6e5729fd87f86fe7d8bbcb6163e707ec2e5da..62147900daab716b57ea5134e49c65109c04fa83 100644
--- a/configs/hrnet/faster_rcnn_hrnetv2p_w40_1x.py
+++ b/configs/hrnet/faster_rcnn_hrnetv2p_w40_1x.py
@@ -119,44 +119,51 @@ test_cfg = dict(
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
-img_norm_cfg = dict(mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375], to_rgb=True)
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
- workers_per_gpu=4,
+ workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/hrnet/fcos_hrnetv2p_w32_gn_1x_4gpu.py b/configs/hrnet/fcos_hrnetv2p_w32_gn_1x_4gpu.py
index d7a68177ad9fc6cc2ce3d9303df390182dd26184..f91df1fb08775b5a972bd49d3e3d20194d089557 100644
--- a/configs/hrnet/fcos_hrnetv2p_w32_gn_1x_4gpu.py
+++ b/configs/hrnet/fcos_hrnetv2p_w32_gn_1x_4gpu.py
@@ -9,8 +9,8 @@ model = dict(
num_modules=1,
num_branches=1,
block='BOTTLENECK',
- num_blocks=(4,),
- num_channels=(64,)),
+ num_blocks=(4, ),
+ num_channels=(64, )),
stage2=dict(
num_modules=1,
num_branches=2,
@@ -73,6 +73,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=4,
workers_per_gpu=4,
@@ -80,36 +105,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
diff --git a/configs/hrnet/htc_hrnetv2p_w32_20e.py b/configs/hrnet/htc_hrnetv2p_w32_20e.py
index 3de5b4fb81bbcd97b2c0fc386d6ac207c0ab7661..b1f9ff567f7e2ecb94b89ee930585f41ddc96f37 100644
--- a/configs/hrnet/htc_hrnetv2p_w32_20e.py
+++ b/configs/hrnet/htc_hrnetv2p_w32_20e.py
@@ -32,10 +32,7 @@ model = dict(
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(32, 64, 128, 256)))),
- neck=dict(
- type='HRFPN',
- in_channels=[32, 64, 128, 256],
- out_channels=256),
+ neck=dict(type='HRFPN', in_channels=[32, 64, 128, 256], out_channels=256),
rpn_head=dict(
type='RPNHead',
in_channels=256,
@@ -65,13 +62,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -83,13 +75,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -101,13 +88,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -232,6 +214,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -239,38 +250,18 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
seg_prefix=data_root + 'stuffthingmaps/train2017/',
- seg_scale_factor=1 / 8,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/hrnet/mask_rcnn_hrnetv2p_w18_1x.py b/configs/hrnet/mask_rcnn_hrnetv2p_w18_1x.py
index e8dcfe4dab7df5586ba5e4167a83fa4e41c20c89..153ce55e54e5329a4cd7fed284d8463e249cc239 100644
--- a/configs/hrnet/mask_rcnn_hrnetv2p_w18_1x.py
+++ b/configs/hrnet/mask_rcnn_hrnetv2p_w18_1x.py
@@ -9,8 +9,8 @@ model = dict(
num_modules=1,
num_branches=1,
block='BOTTLENECK',
- num_blocks=(4,),
- num_channels=(64,)),
+ num_blocks=(4, ),
+ num_channels=(64, )),
stage2=dict(
num_modules=1,
num_branches=2,
@@ -29,10 +29,7 @@ model = dict(
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(18, 36, 72, 144)))),
- neck=dict(
- type='HRFPN',
- in_channels=[18, 36, 72, 144],
- out_channels=256),
+ neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256),
rpn_head=dict(
type='RPNHead',
in_channels=256,
@@ -133,8 +130,33 @@ test_cfg = dict(
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
-img_norm_cfg = dict(mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375], to_rgb=True)
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -142,35 +164,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
# if you use 8 GPUs for training, please change lr to 0.02
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
diff --git a/configs/hrnet/mask_rcnn_hrnetv2p_w32_1x.py b/configs/hrnet/mask_rcnn_hrnetv2p_w32_1x.py
index 3abf2b2c918deb4cadfce9591ff65d13f481810d..a334ca3fcc30d076cb15c6b5f3dfc5c61d124b21 100644
--- a/configs/hrnet/mask_rcnn_hrnetv2p_w32_1x.py
+++ b/configs/hrnet/mask_rcnn_hrnetv2p_w32_1x.py
@@ -9,8 +9,8 @@ model = dict(
num_modules=1,
num_branches=1,
block='BOTTLENECK',
- num_blocks=(4,),
- num_channels=(64,)),
+ num_blocks=(4, ),
+ num_channels=(64, )),
stage2=dict(
num_modules=1,
num_branches=2,
@@ -29,10 +29,7 @@ model = dict(
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(32, 64, 128, 256)))),
- neck=dict(
- type='HRFPN',
- in_channels=[32, 64, 128, 256],
- out_channels=256),
+ neck=dict(type='HRFPN', in_channels=[32, 64, 128, 256], out_channels=256),
rpn_head=dict(
type='RPNHead',
in_channels=256,
@@ -132,8 +129,33 @@ test_cfg = dict(
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
-img_norm_cfg = dict(mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375], to_rgb=True)
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -141,35 +163,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/htc/htc_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_20e.py b/configs/htc/htc_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_20e.py
index 4c9581906390864a3bfef5ce87fd279ff35d2532..f06904c531d6c1972a27c5f59bd0329610603914 100644
--- a/configs/htc/htc_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_20e.py
+++ b/configs/htc/htc_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_20e.py
@@ -54,13 +54,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -72,13 +67,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -90,13 +80,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -221,6 +206,39 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+ dict(
+ type='Resize',
+ img_scale=[(1600, 400), (1600, 1400)],
+ multiscale_mode='range',
+ keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=1,
workers_per_gpu=1,
@@ -228,39 +246,18 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=[(1600, 400), (1600, 1400)],
- multiscale_mode='range',
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
seg_prefix=data_root + 'stuffthingmaps/train2017/',
- seg_scale_factor=1 / 8,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/htc/htc_r101_fpn_20e.py b/configs/htc/htc_r101_fpn_20e.py
index de6711d6caf757314173783d7c986ebf41bbb81e..36584a3db62f1573b83ad6dd2fc16c47914ef2da 100644
--- a/configs/htc/htc_r101_fpn_20e.py
+++ b/configs/htc/htc_r101_fpn_20e.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -213,6 +198,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -220,38 +234,18 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
seg_prefix=data_root + 'stuffthingmaps/train2017/',
- seg_scale_factor=1 / 8,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/htc/htc_r50_fpn_1x.py b/configs/htc/htc_r50_fpn_1x.py
index 02da445b353fde27308e228092edf4d073ec34f3..d77d60c7c9da85248cd271379ec268ff36e08ba4 100644
--- a/configs/htc/htc_r50_fpn_1x.py
+++ b/configs/htc/htc_r50_fpn_1x.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -213,6 +198,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -220,38 +234,18 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
seg_prefix=data_root + 'stuffthingmaps/train2017/',
- seg_scale_factor=1 / 8,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/htc/htc_r50_fpn_20e.py b/configs/htc/htc_r50_fpn_20e.py
index 4410a5506c447a0d8bd9cebd3b5dd137c2cd773a..9bc49afa39ce638488ae7bbe5b99042edc3b5abf 100644
--- a/configs/htc/htc_r50_fpn_20e.py
+++ b/configs/htc/htc_r50_fpn_20e.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -213,6 +198,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -220,38 +234,18 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
seg_prefix=data_root + 'stuffthingmaps/train2017/',
- seg_scale_factor=1 / 8,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/htc/htc_without_semantic_r50_fpn_1x.py b/configs/htc/htc_without_semantic_r50_fpn_1x.py
index 8adbe366a52fe4b91eb4f2ea90a18fb4fa7fbc15..2a4b7771274c952547f8dbc42f2878a1872a6bd8 100644
--- a/configs/htc/htc_without_semantic_r50_fpn_1x.py
+++ b/configs/htc/htc_without_semantic_r50_fpn_1x.py
@@ -46,13 +46,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -64,13 +59,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -82,13 +72,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -198,6 +183,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -205,35 +215,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/htc/htc_x101_32x4d_fpn_20e_16gpu.py b/configs/htc/htc_x101_32x4d_fpn_20e_16gpu.py
index 2846c572d6ac36c44043156e526b3e807250c44d..830a655813ac58f3812ca7ef6f99d2c7a4ecc614 100644
--- a/configs/htc/htc_x101_32x4d_fpn_20e_16gpu.py
+++ b/configs/htc/htc_x101_32x4d_fpn_20e_16gpu.py
@@ -215,6 +215,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=1,
workers_per_gpu=1,
@@ -222,38 +251,18 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
seg_prefix=data_root + 'stuffthingmaps/train2017/',
- seg_scale_factor=1 / 8,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/htc/htc_x101_64x4d_fpn_20e_16gpu.py b/configs/htc/htc_x101_64x4d_fpn_20e_16gpu.py
index 095a81b549c878d41507178e5a68566c9a31d80f..6c5dada91b2976d66b5b0f581ef0a83cbf31739b 100644
--- a/configs/htc/htc_x101_64x4d_fpn_20e_16gpu.py
+++ b/configs/htc/htc_x101_64x4d_fpn_20e_16gpu.py
@@ -48,13 +48,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -66,13 +61,8 @@ model = dict(
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0)),
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
@@ -84,13 +74,8 @@ model = dict(
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(
- type='SmoothL1Loss',
- beta=1.0,
- loss_weight=1.0))
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
@@ -215,6 +200,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='SegResizeFlipPadRescale', scale_factor=1 / 8),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=1,
workers_per_gpu=1,
@@ -222,38 +236,18 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
seg_prefix=data_root + 'stuffthingmaps/train2017/',
- seg_scale_factor=1 / 8,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/libra_rcnn/libra_fast_rcnn_r50_fpn_1x.py b/configs/libra_rcnn/libra_fast_rcnn_r50_fpn_1x.py
index 365c0145b4c5b6de0e14dd4850bbe50d96371111..5855f2395c0272ef29699d1fa45426f0f50ca1cf 100644
--- a/configs/libra_rcnn/libra_fast_rcnn_r50_fpn_1x.py
+++ b/configs/libra_rcnn/libra_fast_rcnn_r50_fpn_1x.py
@@ -75,46 +75,55 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=2000),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadProposals', num_max_proposals=None),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img', 'proposals']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
- workers_per_gpu=0,
+ workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
- img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
proposal_file=data_root +
'libra_proposals/rpn_r50_fpn_1x_train2017.pkl',
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'train2017/',
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'libra_proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
- img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
proposal_file=data_root + 'libra_proposals/rpn_r50_fpn_1x_val2017.pkl',
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ img_prefix=data_root + 'val2017/',
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/libra_rcnn/libra_faster_rcnn_r101_fpn_1x.py b/configs/libra_rcnn/libra_faster_rcnn_r101_fpn_1x.py
index 38af55dcaca794a497aa00e492c12b8b34dd2bc2..fec7052161e6423cff6cc8472c4d243c2eee11d4 100644
--- a/configs/libra_rcnn/libra_faster_rcnn_r101_fpn_1x.py
+++ b/configs/libra_rcnn/libra_faster_rcnn_r101_fpn_1x.py
@@ -120,6 +120,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -127,35 +152,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/libra_rcnn/libra_faster_rcnn_r50_fpn_1x.py b/configs/libra_rcnn/libra_faster_rcnn_r50_fpn_1x.py
index 2ab33dce9ed3206c028e0a1030578f84ebde923c..8e1284a6e597b079a73f2fb8e4055bb4e3bc6a37 100644
--- a/configs/libra_rcnn/libra_faster_rcnn_r50_fpn_1x.py
+++ b/configs/libra_rcnn/libra_faster_rcnn_r50_fpn_1x.py
@@ -120,6 +120,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -127,35 +152,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/libra_rcnn/libra_faster_rcnn_x101_64x4d_fpn_1x.py b/configs/libra_rcnn/libra_faster_rcnn_x101_64x4d_fpn_1x.py
index 26172a486263d29c2b664e54a0d6bd81e99c5829..fbd50c0425d258c6fce94726214847da162cbf8b 100644
--- a/configs/libra_rcnn/libra_faster_rcnn_x101_64x4d_fpn_1x.py
+++ b/configs/libra_rcnn/libra_faster_rcnn_x101_64x4d_fpn_1x.py
@@ -122,6 +122,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -129,35 +154,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/libra_rcnn/libra_retinanet_r50_fpn_1x.py b/configs/libra_rcnn/libra_retinanet_r50_fpn_1x.py
index 1e0cab929591f0cea539ebcf5f99aa2a8a4b2f49..ab36054481b7d6f3c4b88c8de1f203b5dd966c90 100644
--- a/configs/libra_rcnn/libra_retinanet_r50_fpn_1x.py
+++ b/configs/libra_rcnn/libra_retinanet_r50_fpn_1x.py
@@ -74,6 +74,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -81,36 +106,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/mask_rcnn_r101_fpn_1x.py b/configs/mask_rcnn_r101_fpn_1x.py
index 2840be7b392679e3884eb7c7ad72662efe03a257..280808cf92f4a922810b0e298f48951c4e2e60a7 100644
--- a/configs/mask_rcnn_r101_fpn_1x.py
+++ b/configs/mask_rcnn_r101_fpn_1x.py
@@ -116,6 +116,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -123,35 +148,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/mask_rcnn_r50_caffe_c4_1x.py b/configs/mask_rcnn_r50_caffe_c4_1x.py
index f901c51904f5aff605e6b5ce47af18a974dde38a..15fdafb0e95c4ef8c311ed7ce8625e8f61fbb559 100644
--- a/configs/mask_rcnn_r50_caffe_c4_1x.py
+++ b/configs/mask_rcnn_r50_caffe_c4_1x.py
@@ -120,42 +120,49 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
- imgs_per_gpu=1,
+ imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/mask_rcnn_r50_fpn_1x.py b/configs/mask_rcnn_r50_fpn_1x.py
index 59a84c86a6079c843274b41f099d933f2706cb36..04f6d22ef1ef1df218450faba7d8f07422708c01 100644
--- a/configs/mask_rcnn_r50_fpn_1x.py
+++ b/configs/mask_rcnn_r50_fpn_1x.py
@@ -116,6 +116,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -123,35 +148,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/mask_rcnn_x101_32x4d_fpn_1x.py b/configs/mask_rcnn_x101_32x4d_fpn_1x.py
index 051801b36f4894e63e922671d3148f2976612fdd..74d6823f6beba6807c8ce2dc35c0c7984d85957b 100644
--- a/configs/mask_rcnn_x101_32x4d_fpn_1x.py
+++ b/configs/mask_rcnn_x101_32x4d_fpn_1x.py
@@ -118,6 +118,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -125,35 +150,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/mask_rcnn_x101_64x4d_fpn_1x.py b/configs/mask_rcnn_x101_64x4d_fpn_1x.py
index 434bf6922608c927717a5454fb406e4bc3640bfb..18e4244c8c77d2e452e93e6ae13f004a5d629dbf 100644
--- a/configs/mask_rcnn_x101_64x4d_fpn_1x.py
+++ b/configs/mask_rcnn_x101_64x4d_fpn_1x.py
@@ -118,6 +118,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -125,35 +150,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/ms_rcnn/ms_rcnn_r101_caffe_fpn_1x.py b/configs/ms_rcnn/ms_rcnn_r101_caffe_fpn_1x.py
index 682d308a937675bc2a03c59982ab853bd7c39b15..0a523f62333383b30e28db21cc5feca367d87f7a 100644
--- a/configs/ms_rcnn/ms_rcnn_r101_caffe_fpn_1x.py
+++ b/configs/ms_rcnn/ms_rcnn_r101_caffe_fpn_1x.py
@@ -127,6 +127,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -134,35 +159,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/ms_rcnn/ms_rcnn_r50_caffe_fpn_1x.py b/configs/ms_rcnn/ms_rcnn_r50_caffe_fpn_1x.py
index 16ebde50bfcc25b79447dc894352a8d48638d40b..6f2a7916ecf4140631576d91e3e645a2d1a92950 100644
--- a/configs/ms_rcnn/ms_rcnn_r50_caffe_fpn_1x.py
+++ b/configs/ms_rcnn/ms_rcnn_r50_caffe_fpn_1x.py
@@ -127,6 +127,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -134,35 +159,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x.py b/configs/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x.py
index a6b720332cf33263295dcfeeae0d85b793e5166d..009b0ad3a8257b401d3dd5a3b0299fd05481cda4 100644
--- a/configs/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x.py
+++ b/configs/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x.py
@@ -128,6 +128,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -135,35 +160,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py b/configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py
index 07e72ffdfda661f7406386f43f63c03abe5f180c..b4b533a2b300efce356d7e6542f52ed0b997f8de 100644
--- a/configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py
+++ b/configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py
@@ -102,11 +102,36 @@ dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1000, 600),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
- type='RepeatDataset', # to avoid reloading datasets frequently
+ type='RepeatDataset',
times=3,
dataset=dict(
type=dataset_type,
@@ -115,35 +140,17 @@ data = dict(
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
- img_scale=(1000, 600),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True)),
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
- img_scale=(1000, 600),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
- img_scale=(1000, 600),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/pascal_voc/ssd300_voc.py b/configs/pascal_voc/ssd300_voc.py
index 551ecda3cb6ecc658aa9107d5af991977dc8b4af..2a5756d5fe0cc366d531a662391309c28d2c963d 100644
--- a/configs/pascal_voc/ssd300_voc.py
+++ b/configs/pascal_voc/ssd300_voc.py
@@ -23,6 +23,7 @@ model = dict(
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
+# model training and testing settings
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
@@ -42,14 +43,50 @@ test_cfg = dict(
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
-# model training and testing settings
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile', to_float32=True),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='PhotoMetricDistortion',
+ brightness_delta=32,
+ contrast_range=(0.5, 1.5),
+ saturation_range=(0.5, 1.5),
+ hue_delta=18),
+ dict(
+ type='Expand',
+ mean=img_norm_cfg['mean'],
+ to_rgb=img_norm_cfg['to_rgb'],
+ ratio_range=(1, 4)),
+ dict(
+ type='MinIoURandomCrop',
+ min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+ min_crop_size=0.3),
+ dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(300, 300),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
- imgs_per_gpu=4,
- workers_per_gpu=2,
+ imgs_per_gpu=8,
+ workers_per_gpu=3,
train=dict(
type='RepeatDataset',
times=10,
@@ -60,51 +97,17 @@ data = dict(
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True,
- test_mode=False,
- extra_aug=dict(
- photo_metric_distortion=dict(
- brightness_delta=32,
- contrast_range=(0.5, 1.5),
- saturation_range=(0.5, 1.5),
- hue_delta=18),
- expand=dict(
- mean=img_norm_cfg['mean'],
- to_rgb=img_norm_cfg['to_rgb'],
- ratio_range=(1, 4)),
- random_crop=dict(
- min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
- resize_keep_ratio=False)),
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
diff --git a/configs/pascal_voc/ssd512_voc.py b/configs/pascal_voc/ssd512_voc.py
index f01404adfa2825b2e938ec6dc3c584b281868075..4fa7df658a755e67c74c3c454bf2f90e4423a9b5 100644
--- a/configs/pascal_voc/ssd512_voc.py
+++ b/configs/pascal_voc/ssd512_voc.py
@@ -23,6 +23,7 @@ model = dict(
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
+# model training and testing settings
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
@@ -42,14 +43,50 @@ test_cfg = dict(
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
-# model training and testing settings
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile', to_float32=True),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='PhotoMetricDistortion',
+ brightness_delta=32,
+ contrast_range=(0.5, 1.5),
+ saturation_range=(0.5, 1.5),
+ hue_delta=18),
+ dict(
+ type='Expand',
+ mean=img_norm_cfg['mean'],
+ to_rgb=img_norm_cfg['to_rgb'],
+ ratio_range=(1, 4)),
+ dict(
+ type='MinIoURandomCrop',
+ min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+ min_crop_size=0.3),
+ dict(type='Resize', img_scale=(512, 512), keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(512, 512),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
- imgs_per_gpu=4,
- workers_per_gpu=2,
+ imgs_per_gpu=8,
+ workers_per_gpu=3,
train=dict(
type='RepeatDataset',
times=10,
@@ -60,51 +97,17 @@ data = dict(
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
- img_scale=(512, 512),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True,
- test_mode=False,
- extra_aug=dict(
- photo_metric_distortion=dict(
- brightness_delta=32,
- contrast_range=(0.5, 1.5),
- saturation_range=(0.5, 1.5),
- hue_delta=18),
- expand=dict(
- mean=img_norm_cfg['mean'],
- to_rgb=img_norm_cfg['to_rgb'],
- ratio_range=(1, 4)),
- random_crop=dict(
- min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
- resize_keep_ratio=False)),
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
- img_scale=(512, 512),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
- img_scale=(512, 512),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
diff --git a/configs/retinanet_r101_fpn_1x.py b/configs/retinanet_r101_fpn_1x.py
index fb68f933d1245966f55fb73a8852dc33f733da10..837207c85d4316879816eef1c7ed2bbf7ff268e1 100644
--- a/configs/retinanet_r101_fpn_1x.py
+++ b/configs/retinanet_r101_fpn_1x.py
@@ -57,6 +57,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -64,36 +89,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/retinanet_r50_fpn_1x.py b/configs/retinanet_r50_fpn_1x.py
index 2e8246823c7a457ec177aa132fbbb6c1668b0c20..8255d5a33902962079c5bfad48facb3db832fa63 100644
--- a/configs/retinanet_r50_fpn_1x.py
+++ b/configs/retinanet_r50_fpn_1x.py
@@ -57,6 +57,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -64,36 +89,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/retinanet_x101_32x4d_fpn_1x.py b/configs/retinanet_x101_32x4d_fpn_1x.py
index 1b0aaaa5b5ca93e5d580b546160a3ef8dc7cadb5..f31555d9dd38aeda87987d29715c8bda522d5c5e 100644
--- a/configs/retinanet_x101_32x4d_fpn_1x.py
+++ b/configs/retinanet_x101_32x4d_fpn_1x.py
@@ -59,6 +59,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -66,36 +91,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/retinanet_x101_64x4d_fpn_1x.py b/configs/retinanet_x101_64x4d_fpn_1x.py
index f5631f70f3bf87ec9fd21b04c8e318f7856b480a..47c87d6b95d0da60f2258cdfb19f5482df662fe4 100644
--- a/configs/retinanet_x101_64x4d_fpn_1x.py
+++ b/configs/retinanet_x101_64x4d_fpn_1x.py
@@ -59,6 +59,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -66,36 +91,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
diff --git a/configs/rpn_r101_fpn_1x.py b/configs/rpn_r101_fpn_1x.py
index f1eecd2116cf2851204ecfd52ebed934e1e7796e..bcda8c19c748a5798bd8b0d36ea7b2a7d926a403 100644
--- a/configs/rpn_r101_fpn_1x.py
+++ b/configs/rpn_r101_fpn_1x.py
@@ -57,6 +57,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -64,35 +89,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/rpn_r50_caffe_c4_1x.py b/configs/rpn_r50_caffe_c4_1x.py
index caf0108be344c8a0a69b84222a456a3e0af795f0..3d7d15b589bda64527ee5705424720352f8b7496 100644
--- a/configs/rpn_r50_caffe_c4_1x.py
+++ b/configs/rpn_r50_caffe_c4_1x.py
@@ -57,6 +57,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -64,35 +89,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/rpn_r50_fpn_1x.py b/configs/rpn_r50_fpn_1x.py
index 96e71e08ea2b4bc6444f7aa20c51de67c0007928..b8928257591ab7f4503bf5fb1ca105ef60e15f0d 100644
--- a/configs/rpn_r50_fpn_1x.py
+++ b/configs/rpn_r50_fpn_1x.py
@@ -57,6 +57,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -64,35 +89,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/rpn_x101_32x4d_fpn_1x.py b/configs/rpn_x101_32x4d_fpn_1x.py
index 2a3faef55293a970b3b857d815f9c5394e55865b..709b5de56bb5fd759c1e1104ae2105ac949ffd45 100644
--- a/configs/rpn_x101_32x4d_fpn_1x.py
+++ b/configs/rpn_x101_32x4d_fpn_1x.py
@@ -59,6 +59,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -66,35 +91,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/rpn_x101_64x4d_fpn_1x.py b/configs/rpn_x101_64x4d_fpn_1x.py
index 182a0b39530b579cbd0c681aaad5072dce9e3a4a..b2946d10aee77b16b3d1067ab068606cceb1c137 100644
--- a/configs/rpn_x101_64x4d_fpn_1x.py
+++ b/configs/rpn_x101_64x4d_fpn_1x.py
@@ -59,6 +59,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_label=False),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -66,35 +91,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=False,
- with_label=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
diff --git a/configs/scratch/scratch_faster_rcnn_r50_fpn_gn_6x.py b/configs/scratch/scratch_faster_rcnn_r50_fpn_gn_6x.py
index cbb0e232acab00aad5bfad724ad9cb12e006ee7e..5621d077d3ae7cdeef181e060483321c7580e085 100644
--- a/configs/scratch/scratch_faster_rcnn_r50_fpn_gn_6x.py
+++ b/configs/scratch/scratch_faster_rcnn_r50_fpn_gn_6x.py
@@ -107,6 +107,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -114,35 +139,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
diff --git a/configs/scratch/scratch_mask_rcnn_r50_fpn_gn_6x.py b/configs/scratch/scratch_mask_rcnn_r50_fpn_gn_6x.py
index 97a7ef2a7ce173f0c44a59a2474f96cc89118f72..321619d9825801d181fd2a1b47fe10cefb4aaa95 100644
--- a/configs/scratch/scratch_mask_rcnn_r50_fpn_gn_6x.py
+++ b/configs/scratch/scratch_mask_rcnn_r50_fpn_gn_6x.py
@@ -124,6 +124,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
@@ -131,35 +156,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0.5,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(1333, 800),
- img_norm_cfg=img_norm_cfg,
- size_divisor=32,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='SGD',
diff --git a/configs/ssd300_coco.py b/configs/ssd300_coco.py
index e48a6e69be192a5ed806b9170931936cc524f712..f34d52e1b2d2a39723bf183c6a140ca2f808df2f 100644
--- a/configs/ssd300_coco.py
+++ b/configs/ssd300_coco.py
@@ -47,6 +47,43 @@ test_cfg = dict(
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile', to_float32=True),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='PhotoMetricDistortion',
+ brightness_delta=32,
+ contrast_range=(0.5, 1.5),
+ saturation_range=(0.5, 1.5),
+ hue_delta=18),
+ dict(
+ type='Expand',
+ mean=img_norm_cfg['mean'],
+ to_rgb=img_norm_cfg['to_rgb'],
+ ratio_range=(1, 4)),
+ dict(
+ type='MinIoURandomCrop',
+ min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+ min_crop_size=0.3),
+ dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(300, 300),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=8,
workers_per_gpu=3,
@@ -57,51 +94,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True,
- test_mode=False,
- extra_aug=dict(
- photo_metric_distortion=dict(
- brightness_delta=32,
- contrast_range=(0.5, 1.5),
- saturation_range=(0.5, 1.5),
- hue_delta=18),
- expand=dict(
- mean=img_norm_cfg['mean'],
- to_rgb=img_norm_cfg['to_rgb'],
- ratio_range=(1, 4)),
- random_crop=dict(
- min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
- resize_keep_ratio=False)),
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
diff --git a/configs/ssd512_coco.py b/configs/ssd512_coco.py
index 58242631b2474ae4c1b3be6e7875e676e6c698ef..67fe0309c6bd3b05bf151011685dbd40ca732b91 100644
--- a/configs/ssd512_coco.py
+++ b/configs/ssd512_coco.py
@@ -47,6 +47,43 @@ test_cfg = dict(
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile', to_float32=True),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='PhotoMetricDistortion',
+ brightness_delta=32,
+ contrast_range=(0.5, 1.5),
+ saturation_range=(0.5, 1.5),
+ hue_delta=18),
+ dict(
+ type='Expand',
+ mean=img_norm_cfg['mean'],
+ to_rgb=img_norm_cfg['to_rgb'],
+ ratio_range=(1, 4)),
+ dict(
+ type='MinIoURandomCrop',
+ min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+ min_crop_size=0.3),
+ dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(300, 300),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=8,
workers_per_gpu=3,
@@ -57,51 +94,17 @@ data = dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
- img_scale=(512, 512),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True,
- test_mode=False,
- extra_aug=dict(
- photo_metric_distortion=dict(
- brightness_delta=32,
- contrast_range=(0.5, 1.5),
- saturation_range=(0.5, 1.5),
- hue_delta=18),
- expand=dict(
- mean=img_norm_cfg['mean'],
- to_rgb=img_norm_cfg['to_rgb'],
- ratio_range=(1, 4)),
- random_crop=dict(
- min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
- resize_keep_ratio=False)),
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(512, 512),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
- img_scale=(512, 512),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
diff --git a/configs/wider_face/ssd300_wider_face.py b/configs/wider_face/ssd300_wider_face.py
index 53cafc1ef2ea269e3a98208de3e6fefc03a94837..6a4184e1d874aaf1d40eb2410bc5cbd76947cede 100644
--- a/configs/wider_face/ssd300_wider_face.py
+++ b/configs/wider_face/ssd300_wider_face.py
@@ -23,6 +23,7 @@ model = dict(
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
+# model training and testing settings
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
@@ -42,11 +43,47 @@ test_cfg = dict(
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
-# model training and testing settings
# dataset settings
dataset_type = 'WIDERFaceDataset'
data_root = 'data/WIDERFace/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile', to_float32=True),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(
+ type='PhotoMetricDistortion',
+ brightness_delta=32,
+ contrast_range=(0.5, 1.5),
+ saturation_range=(0.5, 1.5),
+ hue_delta=18),
+ dict(
+ type='Expand',
+ mean=img_norm_cfg['mean'],
+ to_rgb=img_norm_cfg['to_rgb'],
+ ratio_range=(1, 4)),
+ dict(
+ type='MinIoURandomCrop',
+ min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
+ min_crop_size=0.3),
+ dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(300, 300),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=False),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
data = dict(
imgs_per_gpu=60,
workers_per_gpu=2,
@@ -55,57 +92,20 @@ data = dict(
times=2,
dataset=dict(
type=dataset_type,
- ann_file=[
- data_root + 'train.txt',
- ],
- img_prefix=[data_root + 'WIDER_train/'],
- img_scale=(300, 300),
- min_size=17, # throw away very small faces to improve training,
- # because 300x300 is too low resolution to detect them
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0.5,
- with_mask=False,
- with_crowd=False,
- with_label=True,
- test_mode=False,
- extra_aug=dict(
- photo_metric_distortion=dict(
- brightness_delta=32,
- contrast_range=(0.5, 1.5),
- saturation_range=(0.5, 1.5),
- hue_delta=18),
- expand=dict(
- mean=img_norm_cfg['mean'],
- to_rgb=img_norm_cfg['to_rgb'],
- ratio_range=(1, 4)),
- random_crop=dict(
- min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
- resize_keep_ratio=False)),
+ ann_file=data_root + 'train.txt',
+ img_prefix=data_root + 'WIDER_train/',
+ min_size=17,
+ pipeline=train_pipeline)),
val=dict(
type=dataset_type,
- ann_file=data_root + '/val.txt',
+ ann_file=data_root + 'val.txt',
img_prefix=data_root + 'WIDER_val/',
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False),
+ pipeline=test_pipeline),
test=dict(
type=dataset_type,
- ann_file=data_root + '/val.txt',
+ ann_file=data_root + 'val.txt',
img_prefix=data_root + 'WIDER_val/',
- img_scale=(300, 300),
- img_norm_cfg=img_norm_cfg,
- size_divisor=None,
- flip_ratio=0,
- with_mask=False,
- with_label=False,
- test_mode=True,
- resize_keep_ratio=False))
+ pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
@@ -122,7 +122,7 @@ log_config = dict(
interval=1,
hooks=[
dict(type='TextLoggerHook'),
- dict(type='TensorboardLoggerHook')
+ # dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
diff --git a/demo/data_pipeline.png b/demo/data_pipeline.png
new file mode 100644
index 0000000000000000000000000000000000000000..6ac3fee2bc62753681b2e42a9705dd7eefbee443
Binary files /dev/null and b/demo/data_pipeline.png differ
diff --git a/docs/DATA_PIPELINE.md b/docs/DATA_PIPELINE.md
new file mode 100644
index 0000000000000000000000000000000000000000..413463abd8e0a45163506aa4ea37a703ec81fcee
--- /dev/null
+++ b/docs/DATA_PIPELINE.md
@@ -0,0 +1,115 @@
+## Data preparation pipeline
+
+The data preparation pipeline and the dataset is decomposed. Usually a dataset
+defines how to process the annotations and a data pipeline defines all the steps to prepare a data dict.
+A pipeline consists of a sequence of operations. Each operation takes a dict as input and also output a dict for the next transform.
+
+We present a classical pipeline in the following figure. The blue blocks are pipeline operations. With the pipeline going on, each operator can add new keys (marked as green) to the result dict or update the existing keys (marked as orange).
+
+
+The operations are categorized into data loading, pre-processing, formatting and test-time augmentation.
+
+Here is an pipeline example for Faster R-CNN.
+```python
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(1333, 800),
+ flip=False,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip'),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
+```
+
+For each operation, we list the related dict fields that are added/updated/removed.
+
+### Data loading
+
+`LoadImageFromFile`
+- add: img, img_shape, ori_shape
+
+`LoadAnnotations`
+- add: gt_bboxes, gt_bboxes_ignore, gt_labels, gt_masks, gt_semantic_seg, bbox_fields, mask_fields
+
+`LoadProposals`
+- add: proposals
+
+### Pre-processing
+
+`Resize`
+- add: scale, scale_idx, pad_shape, scale_factor, keep_ratio
+- update: img, img_shape, *bbox_fields, *mask_fields
+
+`RandomFlip`
+- add: flip
+- update: img, *bbox_fields, *mask_fields
+
+`Pad`
+- add: pad_fixed_size, pad_size_divisor
+- update: img, pad_shape, *mask_fields
+
+`RandomCrop`
+- update: img, pad_shape, gt_bboxes, gt_labels, gt_masks, *bbox_fields
+
+`Normalize`
+- add: img_norm_cfg
+- update: img
+
+`SegResizeFlipPadRescale`
+- update: gt_semantic_seg
+
+`PhotoMetricDistortion`
+- update: img
+
+`Expand`
+- update: img, gt_bboxes
+
+`MinIoURandomCrop`
+- update: img, gt_bboxes, gt_labels
+
+`Corrupt`
+- update: img
+
+### Formatting
+
+`ToTensor`
+- update: specified by `keys`.
+
+`ImageToTensor`
+- update: specified by `keys`.
+
+`Transpose`
+- update: specified by `keys`.
+
+`ToDataContainer`
+- update: specified by `fields`.
+
+`DefaultFormatBundle`
+- update: img, proposals, gt_bboxes, gt_bboxes_ignore, gt_labels, gt_masks, gt_semantic_seg
+
+`Collect`
+- add: img_meta (the keys of img_meta is specified by `meta_keys`)
+- remove: all other keys except for those specified by `keys`
+
+### Test time augmentation
+
+`MultiScaleFlipAug`
\ No newline at end of file
diff --git a/docs/GETTING_STARTED.md b/docs/GETTING_STARTED.md
index b603e19e35ffe4d997de37c7bdca00568526e636..5977c7131b5bad829c7d51ee959004d8024d5240 100644
--- a/docs/GETTING_STARTED.md
+++ b/docs/GETTING_STARTED.md
@@ -89,12 +89,10 @@ model = init_detector(config_file, checkpoint_file, device='cuda:0')
# test a single image and show the results
img = 'test.jpg' # or img = mmcv.imread(img), which will only load it once
result = inference_detector(model, img)
+# visualize the results in a new window
show_result(img, result, model.CLASSES)
-
-# test a list of images and write the results to image files
-imgs = ['test1.jpg', 'test2.jpg']
-for i, result in enumerate(inference_detector(model, imgs)):
- show_result(imgs[i], result, model.CLASSES, out_file='result_{}.jpg'.format(i))
+# or save the visualization results to image files
+show_result(img, result, model.CLASSES, out_file='result.jpg')
# test a video and show the results
video = mmcv.VideoReader('video.mp4')
diff --git a/mmdet/apis/inference.py b/mmdet/apis/inference.py
index 85bfd2bfbdcfb613864d2f99fae7ff393ddab1e3..67b2b241404251dc966a9e9322b3ee6975c35d4c 100644
--- a/mmdet/apis/inference.py
+++ b/mmdet/apis/inference.py
@@ -5,11 +5,11 @@ import mmcv
import numpy as np
import pycocotools.mask as maskUtils
import torch
+from mmcv.parallel import collate, scatter
from mmcv.runner import load_checkpoint
from mmdet.core import get_classes
-from mmdet.datasets import to_tensor
-from mmdet.datasets.transforms import ImageTransform
+from mmdet.datasets.pipelines import Compose
from mmdet.models import build_detector
@@ -46,7 +46,16 @@ def init_detector(config, checkpoint=None, device='cuda:0'):
return model
-def inference_detector(model, imgs):
+class LoadImage(object):
+
+ def __call__(self, results):
+ img = mmcv.imread(results['img'])
+ results['img'] = img
+ results['ori_shape'] = img.shape
+ return results
+
+
+def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
@@ -59,45 +68,19 @@ def inference_detector(model, imgs):
detection results directly.
"""
cfg = model.cfg
- img_transform = ImageTransform(
- size_divisor=cfg.data.test.size_divisor, **cfg.img_norm_cfg)
-
device = next(model.parameters()).device # model device
- if not isinstance(imgs, list):
- return _inference_single(model, imgs, img_transform, device)
- else:
- return _inference_generator(model, imgs, img_transform, device)
-
-
-def _prepare_data(img, img_transform, cfg, device):
- ori_shape = img.shape
- img, img_shape, pad_shape, scale_factor = img_transform(
- img,
- scale=cfg.data.test.img_scale,
- keep_ratio=cfg.data.test.get('resize_keep_ratio', True))
- img = to_tensor(img).to(device).unsqueeze(0)
- img_meta = [
- dict(
- ori_shape=ori_shape,
- img_shape=img_shape,
- pad_shape=pad_shape,
- scale_factor=scale_factor,
- flip=False)
- ]
- return dict(img=[img], img_meta=[img_meta])
-
-
-def _inference_single(model, img, img_transform, device):
- img = mmcv.imread(img)
- data = _prepare_data(img, img_transform, model.cfg, device)
+ # build the data pipeline
+ test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
+ test_pipeline = Compose(test_pipeline)
+ # prepare data
+ data = dict(img=img)
+ data = test_pipeline(data)
+ data = scatter(collate([data], samples_per_gpu=1), [device])[0]
+ # forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
- return result
-
-def _inference_generator(model, imgs, img_transform, device):
- for img in imgs:
- yield _inference_single(model, img, img_transform, device)
+ return result
# TODO: merge this method with the one in BaseDetector
diff --git a/mmdet/core/evaluation/eval_hooks.py b/mmdet/core/evaluation/eval_hooks.py
index c37f7bd0291474d1411cc4e5f0799bf6959385f5..6cf87ffe40b6d7fc13e6278807e6a6e8a6af7b27 100644
--- a/mmdet/core/evaluation/eval_hooks.py
+++ b/mmdet/core/evaluation/eval_hooks.py
@@ -78,12 +78,12 @@ class DistEvalmAPHook(DistEvalHook):
def evaluate(self, runner, results):
gt_bboxes = []
gt_labels = []
- gt_ignore = [] if self.dataset.with_crowd else None
+ gt_ignore = []
for i in range(len(self.dataset)):
ann = self.dataset.get_ann_info(i)
bboxes = ann['bboxes']
labels = ann['labels']
- if gt_ignore is not None:
+ if 'bboxes_ignore' in ann:
ignore = np.concatenate([
np.zeros(bboxes.shape[0], dtype=np.bool),
np.ones(ann['bboxes_ignore'].shape[0], dtype=np.bool)
@@ -93,6 +93,8 @@ class DistEvalmAPHook(DistEvalHook):
labels = np.concatenate([labels, ann['labels_ignore']])
gt_bboxes.append(bboxes)
gt_labels.append(labels)
+ if not gt_ignore:
+ gt_ignore = None
# If the dataset is VOC2007, then use 11 points mAP evaluation.
if hasattr(self.dataset, 'year') and self.dataset.year == 2007:
ds_name = 'voc07'
diff --git a/mmdet/datasets/__init__.py b/mmdet/datasets/__init__.py
index 11b7569ac2e67af993c6faa939b75f4aa64136bc..8de55d26b02760378c3f1ffd63201ba69c0d6785 100644
--- a/mmdet/datasets/__init__.py
+++ b/mmdet/datasets/__init__.py
@@ -6,7 +6,6 @@ from .dataset_wrappers import ConcatDataset, RepeatDataset
from .extra_aug import ExtraAugmentation
from .loader import DistributedGroupSampler, GroupSampler, build_dataloader
from .registry import DATASETS
-from .utils import random_scale, show_ann, to_tensor
from .voc import VOCDataset
from .wider_face import WIDERFaceDataset
from .xml_style import XMLDataset
@@ -14,7 +13,6 @@ from .xml_style import XMLDataset
__all__ = [
'CustomDataset', 'XMLDataset', 'CocoDataset', 'VOCDataset',
'CityscapesDataset', 'GroupSampler', 'DistributedGroupSampler',
- 'build_dataloader', 'to_tensor', 'random_scale', 'show_ann',
- 'ConcatDataset', 'RepeatDataset', 'ExtraAugmentation', 'WIDERFaceDataset',
- 'DATASETS', 'build_dataset'
+ 'build_dataloader', 'ConcatDataset', 'RepeatDataset', 'ExtraAugmentation',
+ 'WIDERFaceDataset', 'DATASETS', 'build_dataset'
]
diff --git a/mmdet/datasets/coco.py b/mmdet/datasets/coco.py
index 46ef7099a8ff39cb3d4dd2cc9e410af955922cf7..23c9120e4917e9714b73068bb4e19abcc94d9c3a 100644
--- a/mmdet/datasets/coco.py
+++ b/mmdet/datasets/coco.py
@@ -42,7 +42,7 @@ class CocoDataset(CustomDataset):
img_id = self.img_infos[idx]['id']
ann_ids = self.coco.getAnnIds(imgIds=[img_id])
ann_info = self.coco.loadAnns(ann_ids)
- return self._parse_ann_info(ann_info, self.with_mask)
+ return self._parse_ann_info(self.img_infos[idx], ann_info)
def _filter_imgs(self, min_size=32):
"""Filter images too small or without ground truths."""
@@ -55,7 +55,7 @@ class CocoDataset(CustomDataset):
valid_inds.append(i)
return valid_inds
- def _parse_ann_info(self, ann_info, with_mask=True):
+ def _parse_ann_info(self, img_info, ann_info):
"""Parse bbox and mask annotation.
Args:
@@ -64,19 +64,14 @@ class CocoDataset(CustomDataset):
Returns:
dict: A dict containing the following keys: bboxes, bboxes_ignore,
- labels, masks, mask_polys, poly_lens.
+ labels, masks, seg_map. "masks" are raw annotations and not
+ decoded into binary masks.
"""
gt_bboxes = []
gt_labels = []
gt_bboxes_ignore = []
- # Two formats are provided.
- # 1. mask: a binary map of the same size of the image.
- # 2. polys: each mask consists of one or several polys, each poly is a
- # list of float.
- if with_mask:
- gt_masks = []
- gt_mask_polys = []
- gt_poly_lens = []
+ gt_masks_ann = []
+
for i, ann in enumerate(ann_info):
if ann.get('ignore', False):
continue
@@ -84,19 +79,13 @@ class CocoDataset(CustomDataset):
if ann['area'] <= 0 or w < 1 or h < 1:
continue
bbox = [x1, y1, x1 + w - 1, y1 + h - 1]
- if ann['iscrowd']:
+ if ann.get('iscrowd', False):
gt_bboxes_ignore.append(bbox)
else:
gt_bboxes.append(bbox)
gt_labels.append(self.cat2label[ann['category_id']])
- if with_mask:
- gt_masks.append(self.coco.annToMask(ann))
- mask_polys = [
- p for p in ann['segmentation'] if len(p) >= 6
- ] # valid polygons have >= 3 points (6 coordinates)
- poly_lens = [len(p) for p in mask_polys]
- gt_mask_polys.append(mask_polys)
- gt_poly_lens.extend(poly_lens)
+ gt_masks_ann.append(ann['segmentation'])
+
if gt_bboxes:
gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
gt_labels = np.array(gt_labels, dtype=np.int64)
@@ -109,12 +98,13 @@ class CocoDataset(CustomDataset):
else:
gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)
+ seg_map = img_info['filename'].replace('jpg', 'png')
+
ann = dict(
- bboxes=gt_bboxes, labels=gt_labels, bboxes_ignore=gt_bboxes_ignore)
+ bboxes=gt_bboxes,
+ labels=gt_labels,
+ bboxes_ignore=gt_bboxes_ignore,
+ masks=gt_masks_ann,
+ seg_map=seg_map)
- if with_mask:
- ann['masks'] = gt_masks
- # poly format is not used in the current implementation
- ann['mask_polys'] = gt_mask_polys
- ann['poly_lens'] = gt_poly_lens
return ann
diff --git a/mmdet/datasets/custom.py b/mmdet/datasets/custom.py
index aed2bf92749677043412c8b36d7eaaded89f71da..d596943f5dca668f99a61aecce535b2c944a915e 100644
--- a/mmdet/datasets/custom.py
+++ b/mmdet/datasets/custom.py
@@ -1,17 +1,11 @@
import os.path as osp
-import warnings
import mmcv
import numpy as np
-from imagecorruptions import corrupt
-from mmcv.parallel import DataContainer as DC
from torch.utils.data import Dataset
-from .extra_aug import ExtraAugmentation
+from .pipelines import Compose
from .registry import DATASETS
-from .transforms import (BboxTransform, ImageTransform, MaskTransform,
- Numpy2Tensor, SegMapTransform)
-from .utils import random_scale, to_tensor
@DATASETS.register_module
@@ -27,7 +21,7 @@ class CustomDataset(Dataset):
'ann': {
'bboxes': <np.ndarray> (n, 4),
'labels': <np.ndarray> (n, ),
- 'bboxes_ignore': <np.ndarray> (k, 4),
+ 'bboxes_ignore': <np.ndarray> (k, 4), (optional field)
'labels_ignore': <np.ndarray> (k, 4) (optional field)
}
},
@@ -41,33 +35,35 @@ class CustomDataset(Dataset):
def __init__(self,
ann_file,
- img_prefix,
- img_scale,
- img_norm_cfg,
- multiscale_mode='value',
- size_divisor=None,
- proposal_file=None,
- num_max_proposals=1000,
- flip_ratio=0,
- with_mask=True,
- with_crowd=True,
- with_label=True,
- with_semantic_seg=False,
+ pipeline,
+ data_root=None,
+ img_prefix=None,
seg_prefix=None,
- seg_scale_factor=1,
- extra_aug=None,
- resize_keep_ratio=True,
- corruption=None,
- corruption_severity=1,
- skip_img_without_anno=True,
+ proposal_file=None,
test_mode=False):
- # prefix of images path
+ self.ann_file = ann_file
+ self.data_root = data_root
self.img_prefix = img_prefix
+ self.seg_prefix = seg_prefix
+ self.proposal_file = proposal_file
+ self.test_mode = test_mode
+ # join paths if data_root is specified
+ if self.data_root is not None:
+ if not osp.isabs(self.ann_file):
+ self.ann_file = osp.join(self.data_root, self.ann_file)
+ if not (self.img_prefix is None or osp.isabs(self.img_prefix)):
+ self.img_prefix = osp.join(self.data_root, self.img_prefix)
+ if not (self.seg_prefix is None or osp.isabs(self.seg_prefix)):
+ self.seg_prefix = osp.join(self.data_root, self.seg_prefix)
+ if not (self.proposal_file is None
+ or osp.isabs(self.proposal_file)):
+ self.proposal_file = osp.join(self.data_root,
+ self.proposal_file)
# load annotations (and proposals)
- self.img_infos = self.load_annotations(ann_file)
- if proposal_file is not None:
- self.proposals = self.load_proposals(proposal_file)
+ self.img_infos = self.load_annotations(self.ann_file)
+ if self.proposal_file is not None:
+ self.proposals = self.load_proposals(self.proposal_file)
else:
self.proposals = None
# filter images with no annotation during training
@@ -76,67 +72,11 @@ class CustomDataset(Dataset):
self.img_infos = [self.img_infos[i] for i in valid_inds]
if self.proposals is not None:
self.proposals = [self.proposals[i] for i in valid_inds]
-
- # (long_edge, short_edge) or [(long1, short1), (long2, short2), ...]
- self.img_scales = img_scale if isinstance(img_scale,
- list) else [img_scale]
- assert mmcv.is_list_of(self.img_scales, tuple)
- # normalization configs
- self.img_norm_cfg = img_norm_cfg
-
- # multi-scale mode (only applicable for multi-scale training)
- self.multiscale_mode = multiscale_mode
- assert multiscale_mode in ['value', 'range']
-
- # max proposals per image
- self.num_max_proposals = num_max_proposals
- # flip ratio
- self.flip_ratio = flip_ratio
- assert flip_ratio >= 0 and flip_ratio <= 1
- # padding border to ensure the image size can be divided by
- # size_divisor (used for FPN)
- self.size_divisor = size_divisor
-
- # with mask or not (reserved field, takes no effect)
- self.with_mask = with_mask
- # some datasets provide bbox annotations as ignore/crowd/difficult,
- # if `with_crowd` is True, then these info is returned.
- self.with_crowd = with_crowd
- # with label is False for RPN
- self.with_label = with_label
- # with semantic segmentation (stuff) annotation or not
- self.with_seg = with_semantic_seg
- # prefix of semantic segmentation map path
- self.seg_prefix = seg_prefix
- # rescale factor for segmentation maps
- self.seg_scale_factor = seg_scale_factor
- # in test mode or not
- self.test_mode = test_mode
-
# set group flag for the sampler
if not self.test_mode:
self._set_group_flag()
- # transforms
- self.img_transform = ImageTransform(
- size_divisor=self.size_divisor, **self.img_norm_cfg)
- self.bbox_transform = BboxTransform()
- self.mask_transform = MaskTransform()
- self.seg_transform = SegMapTransform(self.size_divisor)
- self.numpy2tensor = Numpy2Tensor()
-
- # if use extra augmentation
- if extra_aug is not None:
- self.extra_aug = ExtraAugmentation(**extra_aug)
- else:
- self.extra_aug = None
-
- # image rescale if keep ratio
- self.resize_keep_ratio = resize_keep_ratio
- self.skip_img_without_anno = skip_img_without_anno
-
- # corruptions
- self.corruption = corruption
- self.corruption_severity = corruption_severity
+ # processing pipeline
+ self.pipeline = Compose(pipeline)
def __len__(self):
return len(self.img_infos)
@@ -150,6 +90,13 @@ class CustomDataset(Dataset):
def get_ann_info(self, idx):
return self.img_infos[idx]['ann']
+ def pre_pipeline(self, results):
+ results['img_prefix'] = self.img_prefix
+ results['seg_prefix'] = self.seg_prefix
+ results['proposal_file'] = self.proposal_file
+ results['bbox_fields'] = []
+ results['mask_fields'] = []
+
def _filter_imgs(self, min_size=32):
"""Filter images too small."""
valid_inds = []
@@ -186,164 +133,17 @@ class CustomDataset(Dataset):
def prepare_train_img(self, idx):
img_info = self.img_infos[idx]
- # load image
- img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
- # corruption
- if self.corruption is not None:
- img = corrupt(
- img,
- severity=self.corruption_severity,
- corruption_name=self.corruption)
- # load proposals if necessary
- if self.proposals is not None:
- proposals = self.proposals[idx][:self.num_max_proposals]
- # TODO: Handle empty proposals properly. Currently images with
- # no proposals are just ignored, but they can be used for
- # training in concept.
- if len(proposals) == 0:
- return None
- if not (proposals.shape[1] == 4 or proposals.shape[1] == 5):
- raise AssertionError(
- 'proposals should have shapes (n, 4) or (n, 5), '
- 'but found {}'.format(proposals.shape))
- if proposals.shape[1] == 5:
- scores = proposals[:, 4, None]
- proposals = proposals[:, :4]
- else:
- scores = None
-
- ann = self.get_ann_info(idx)
- gt_bboxes = ann['bboxes']
- gt_labels = ann['labels']
- if self.with_crowd:
- gt_bboxes_ignore = ann['bboxes_ignore']
-
- # skip the image if there is no valid gt bbox
- if len(gt_bboxes) == 0 and self.skip_img_without_anno:
- warnings.warn('Skip the image "%s" that has no valid gt bbox' %
- osp.join(self.img_prefix, img_info['filename']))
- return None
-
- # extra augmentation
- if self.extra_aug is not None:
- img, gt_bboxes, gt_labels = self.extra_aug(img, gt_bboxes,
- gt_labels)
-
- # apply transforms
- flip = True if np.random.rand() < self.flip_ratio else False
- # randomly sample a scale
- img_scale = random_scale(self.img_scales, self.multiscale_mode)
- img, img_shape, pad_shape, scale_factor = self.img_transform(
- img, img_scale, flip, keep_ratio=self.resize_keep_ratio)
- img = img.copy()
- if self.with_seg:
- gt_seg = mmcv.imread(
- osp.join(self.seg_prefix,
- img_info['filename'].replace('jpg', 'png')),
- flag='unchanged')
- gt_seg = self.seg_transform(gt_seg.squeeze(), img_scale, flip)
- gt_seg = mmcv.imrescale(
- gt_seg, self.seg_scale_factor, interpolation='nearest')
- gt_seg = gt_seg[None, ...]
+ ann_info = self.get_ann_info(idx)
+ results = dict(img_info=img_info, ann_info=ann_info)
if self.proposals is not None:
- proposals = self.bbox_transform(proposals, img_shape, scale_factor,
- flip)
- proposals = np.hstack([proposals, scores
- ]) if scores is not None else proposals
- gt_bboxes = self.bbox_transform(gt_bboxes, img_shape, scale_factor,
- flip)
- if self.with_crowd:
- gt_bboxes_ignore = self.bbox_transform(gt_bboxes_ignore, img_shape,
- scale_factor, flip)
- if self.with_mask:
- gt_masks = self.mask_transform(ann['masks'], pad_shape,
- scale_factor, flip)
-
- ori_shape = (img_info['height'], img_info['width'], 3)
- img_meta = dict(
- ori_shape=ori_shape,
- img_shape=img_shape,
- pad_shape=pad_shape,
- scale_factor=scale_factor,
- flip=flip)
-
- data = dict(
- img=DC(to_tensor(img), stack=True),
- img_meta=DC(img_meta, cpu_only=True),
- gt_bboxes=DC(to_tensor(gt_bboxes)))
- if self.proposals is not None:
- data['proposals'] = DC(to_tensor(proposals))
- if self.with_label:
- data['gt_labels'] = DC(to_tensor(gt_labels))
- if self.with_crowd:
- data['gt_bboxes_ignore'] = DC(to_tensor(gt_bboxes_ignore))
- if self.with_mask:
- data['gt_masks'] = DC(gt_masks, cpu_only=True)
- if self.with_seg:
- data['gt_semantic_seg'] = DC(to_tensor(gt_seg), stack=True)
- return data
+ results['proposals'] = self.proposals[idx]
+ self.pre_pipeline(results)
+ return self.pipeline(results)
def prepare_test_img(self, idx):
- """Prepare an image for testing (multi-scale and flipping)"""
img_info = self.img_infos[idx]
- img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
- # corruption
- if self.corruption is not None:
- img = corrupt(
- img,
- severity=self.corruption_severity,
- corruption_name=self.corruption)
- # load proposals if necessary
- if self.proposals is not None:
- proposal = self.proposals[idx][:self.num_max_proposals]
- if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
- raise AssertionError(
- 'proposals should have shapes (n, 4) or (n, 5), '
- 'but found {}'.format(proposal.shape))
- else:
- proposal = None
-
- def prepare_single(img, scale, flip, proposal=None):
- _img, img_shape, pad_shape, scale_factor = self.img_transform(
- img, scale, flip, keep_ratio=self.resize_keep_ratio)
- _img = to_tensor(_img)
- _img_meta = dict(
- ori_shape=(img_info['height'], img_info['width'], 3),
- img_shape=img_shape,
- pad_shape=pad_shape,
- scale_factor=scale_factor,
- flip=flip)
- if proposal is not None:
- if proposal.shape[1] == 5:
- score = proposal[:, 4, None]
- proposal = proposal[:, :4]
- else:
- score = None
- _proposal = self.bbox_transform(proposal, img_shape,
- scale_factor, flip)
- _proposal = np.hstack([_proposal, score
- ]) if score is not None else _proposal
- _proposal = to_tensor(_proposal)
- else:
- _proposal = None
- return _img, _img_meta, _proposal
-
- imgs = []
- img_metas = []
- proposals = []
- for scale in self.img_scales:
- _img, _img_meta, _proposal = prepare_single(
- img, scale, False, proposal)
- imgs.append(_img)
- img_metas.append(DC(_img_meta, cpu_only=True))
- proposals.append(_proposal)
- if self.flip_ratio > 0:
- _img, _img_meta, _proposal = prepare_single(
- img, scale, True, proposal)
- imgs.append(_img)
- img_metas.append(DC(_img_meta, cpu_only=True))
- proposals.append(_proposal)
- data = dict(img=imgs, img_meta=img_metas)
+ results = dict(img_info=img_info)
if self.proposals is not None:
- data['proposals'] = proposals
- return data
+ results['proposals'] = self.proposals[idx]
+ self.pre_pipeline(results)
+ return self.pipeline(results)
diff --git a/mmdet/datasets/pipelines/__init__.py b/mmdet/datasets/pipelines/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..dd5919e0517fbfdb93fb163a75011f331158f3e1
--- /dev/null
+++ b/mmdet/datasets/pipelines/__init__.py
@@ -0,0 +1,16 @@
+from .compose import Compose
+from .formating import (Collect, ImageToTensor, ToDataContainer, ToTensor,
+ Transpose, to_tensor)
+from .loading import LoadAnnotations, LoadImageFromFile, LoadProposals
+from .test_aug import MultiScaleFlipAug
+from .transforms import (Expand, MinIoURandomCrop, Normalize, Pad,
+ PhotoMetricDistortion, RandomCrop, RandomFlip, Resize,
+ SegResizeFlipPadRescale)
+
+__all__ = [
+ 'Compose', 'to_tensor', 'ToTensor', 'ImageToTensor', 'ToDataContainer',
+ 'Transpose', 'Collect', 'LoadAnnotations', 'LoadImageFromFile',
+ 'LoadProposals', 'MultiScaleFlipAug', 'Resize', 'RandomFlip', 'Pad',
+ 'RandomCrop', 'Normalize', 'SegResizeFlipPadRescale', 'MinIoURandomCrop',
+ 'Expand', 'PhotoMetricDistortion'
+]
diff --git a/mmdet/datasets/pipelines/compose.py b/mmdet/datasets/pipelines/compose.py
new file mode 100644
index 0000000000000000000000000000000000000000..f160eed97e383845bcc4822dfbb102f01eecfefe
--- /dev/null
+++ b/mmdet/datasets/pipelines/compose.py
@@ -0,0 +1,35 @@
+import collections
+
+from mmdet.utils import build_from_cfg
+from ..registry import PIPELINES
+
+
+@PIPELINES.register_module
+class Compose(object):
+
+ def __init__(self, transforms):
+ assert isinstance(transforms, collections.abc.Sequence)
+ self.transforms = []
+ for transform in transforms:
+ if isinstance(transform, dict):
+ transform = build_from_cfg(transform, PIPELINES)
+ self.transforms.append(transform)
+ elif callable(transform):
+ self.transforms.append(transform)
+ else:
+ raise TypeError('transform must be callable or a dict')
+
+ def __call__(self, data):
+ for t in self.transforms:
+ data = t(data)
+ if data is None:
+ return None
+ return data
+
+ def __repr__(self):
+ format_string = self.__class__.__name__ + '('
+ for t in self.transforms:
+ format_string += '\n'
+ format_string += ' {0}'.format(t)
+ format_string += '\n)'
+ return format_string
diff --git a/mmdet/datasets/pipelines/formating.py b/mmdet/datasets/pipelines/formating.py
new file mode 100644
index 0000000000000000000000000000000000000000..f5357f742f9531262bb4382857715f3b26a79d6a
--- /dev/null
+++ b/mmdet/datasets/pipelines/formating.py
@@ -0,0 +1,157 @@
+from collections.abc import Sequence
+
+import mmcv
+import numpy as np
+import torch
+from mmcv.parallel import DataContainer as DC
+
+from ..registry import PIPELINES
+
+
+def to_tensor(data):
+ """Convert objects of various python types to :obj:`torch.Tensor`.
+
+ Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
+ :class:`Sequence`, :class:`int` and :class:`float`.
+ """
+ if isinstance(data, torch.Tensor):
+ return data
+ elif isinstance(data, np.ndarray):
+ return torch.from_numpy(data)
+ elif isinstance(data, Sequence) and not mmcv.is_str(data):
+ return torch.tensor(data)
+ elif isinstance(data, int):
+ return torch.LongTensor([data])
+ elif isinstance(data, float):
+ return torch.FloatTensor([data])
+ else:
+ raise TypeError('type {} cannot be converted to tensor.'.format(
+ type(data)))
+
+
+@PIPELINES.register_module
+class ToTensor(object):
+
+ def __init__(self, keys):
+ self.keys = keys
+
+ def __call__(self, results):
+ for key in self.keys:
+ results[key] = to_tensor(results[key])
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(keys={})'.format(self.keys)
+
+
+@PIPELINES.register_module
+class ImageToTensor(object):
+
+ def __init__(self, keys):
+ self.keys = keys
+
+ def __call__(self, results):
+ for key in self.keys:
+ results[key] = to_tensor(results[key].transpose(2, 0, 1))
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(keys={})'.format(self.keys)
+
+
+@PIPELINES.register_module
+class Transpose(object):
+
+ def __init__(self, keys, order):
+ self.keys = keys
+ self.order = order
+
+ def __call__(self, results):
+ for key in self.keys:
+ results[key] = results[key].transpose(self.order)
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(keys={}, order={})'.format(
+ self.keys, self.order)
+
+
+@PIPELINES.register_module
+class ToDataContainer(object):
+
+ def __init__(self,
+ fields=(dict(key='img', stack=True), dict(key='gt_bboxes'),
+ dict(key='gt_labels'))):
+ self.fields = fields
+
+ def __call__(self, results):
+ for field in self.fields:
+ field = field.copy()
+ key = field.pop('key')
+ results[key] = DC(results[key], **field)
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(fields={})'.format(self.fields)
+
+
+@PIPELINES.register_module
+class DefaultFormatBundle(object):
+ """Default formatting bundle.
+
+ It simplifies the pipeline of formatting common fields, including "img",
+ "proposals", "gt_bboxes", "gt_labels", "gt_masks" and "gt_semantic_seg".
+ These fields are formatted as follows.
+
+ - img: (1)transpose, (2)to tensor, (3)to DataContainer (stack=True)
+ - proposals: (1)to tensor, (2)to DataContainer
+ - gt_bboxes: (1)to tensor, (2)to DataContainer
+ - gt_bboxes_ignore: (1)to tensor, (2)to DataContainer
+ - gt_labels: (1)to tensor, (2)to DataContainer
+ - gt_masks: (1)to tensor, (2)to DataContainer (cpu_only=True)
+ - gt_semantic_seg: (1)unsqueeze dim-0 (2)to tensor,
+ (3)to DataContainer (stack=True)
+ """
+
+ def __call__(self, results):
+ if 'img' in results:
+ img = np.ascontiguousarray(results['img'].transpose(2, 0, 1))
+ results['img'] = DC(to_tensor(img), stack=True)
+ for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
+ if key not in results:
+ continue
+ results[key] = DC(to_tensor(results[key]))
+ if 'gt_masks' in results:
+ results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
+ if 'gt_semantic_seg' in results:
+ results['gt_semantic_seg'] = DC(
+ to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__
+
+
+@PIPELINES.register_module
+class Collect(object):
+
+ def __init__(self,
+ keys,
+ meta_keys=('filename', 'ori_shape', 'img_shape', 'pad_shape',
+ 'scale_factor', 'flip', 'img_norm_cfg')):
+ self.keys = keys
+ self.meta_keys = meta_keys
+
+ def __call__(self, results):
+ data = {}
+ img_meta = {}
+ for key in self.meta_keys:
+ img_meta[key] = results[key]
+ data['img_meta'] = DC(img_meta, cpu_only=True)
+ for key in self.keys:
+ data[key] = results[key]
+ return data
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(keys={}, meta_keys={})'.format(
+ self.keys, self.meta_keys)
diff --git a/mmdet/datasets/pipelines/loading.py b/mmdet/datasets/pipelines/loading.py
new file mode 100644
index 0000000000000000000000000000000000000000..cb5ce387e0d6eaa762a6b3eb72671dc05a804b63
--- /dev/null
+++ b/mmdet/datasets/pipelines/loading.py
@@ -0,0 +1,145 @@
+import os.path as osp
+import warnings
+
+import mmcv
+import numpy as np
+import pycocotools.mask as maskUtils
+
+from ..registry import PIPELINES
+
+
+@PIPELINES.register_module
+class LoadImageFromFile(object):
+
+ def __init__(self, to_float32=False):
+ self.to_float32 = to_float32
+
+ def __call__(self, results):
+ filename = osp.join(results['img_prefix'],
+ results['img_info']['filename'])
+ img = mmcv.imread(filename)
+ if self.to_float32:
+ img = img.astype(np.float32)
+ results['filename'] = filename
+ results['img'] = img
+ results['img_shape'] = img.shape
+ results['ori_shape'] = img.shape
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(to_float32={})'.format(
+ self.to_float32)
+
+
+@PIPELINES.register_module
+class LoadAnnotations(object):
+
+ def __init__(self,
+ with_bbox=True,
+ with_label=True,
+ with_mask=False,
+ with_seg=False,
+ poly2mask=True,
+ skip_img_without_anno=True):
+ self.with_bbox = with_bbox
+ self.with_label = with_label
+ self.with_mask = with_mask
+ self.with_seg = with_seg
+ self.poly2mask = poly2mask
+ self.skip_img_without_anno = skip_img_without_anno
+
+ def _load_bboxes(self, results):
+ ann_info = results['ann_info']
+ results['gt_bboxes'] = ann_info['bboxes']
+ if len(results['gt_bboxes']) == 0 and self.skip_img_without_anno:
+ file_path = osp.join(results['img_prefix'],
+ results['img_info']['filename'])
+ warnings.warn(
+ 'Skip the image "{}" that has no valid gt bbox'.format(
+ file_path))
+ return None
+ results['gt_bboxes_ignore'] = ann_info.get('bboxes_ignore', None)
+ results['bbox_fields'].extend(['gt_bboxes', 'gt_bboxes_ignore'])
+ return results
+
+ def _load_labels(self, results):
+ results['gt_labels'] = results['ann_info']['labels']
+ return results
+
+ def _poly2mask(self, mask_ann, img_h, img_w):
+ if isinstance(mask_ann, list):
+ # polygon -- a single object might consist of multiple parts
+ # we merge all parts into one mask rle code
+ rles = maskUtils.frPyObjects(mask_ann, img_h, img_w)
+ rle = maskUtils.merge(rles)
+ elif isinstance(mask_ann['counts'], list):
+ # uncompressed RLE
+ rle = maskUtils.frPyObjects(mask_ann, img_h, img_w)
+ else:
+ # rle
+ rle = mask_ann
+ mask = maskUtils.decode(rle)
+ return mask
+
+ def _load_masks(self, results):
+ h, w = results['img_info']['height'], results['img_info']['width']
+ gt_masks = results['ann_info']['masks']
+ if self.poly2mask:
+ gt_masks = [self._poly2mask(mask, h, w) for mask in gt_masks]
+ results['gt_masks'] = gt_masks
+ results['mask_fields'].append('gt_masks')
+ return results
+
+ def _load_semantic_seg(self, results):
+ results['gt_semantic_seg'] = mmcv.imread(
+ osp.join(results['seg_prefix'], results['ann_info']['seg_map']),
+ flag='unchanged').squeeze()
+ return results
+
+ def __call__(self, results):
+ if self.with_bbox:
+ results = self._load_bboxes(results)
+ if results is None:
+ return None
+ if self.with_label:
+ results = self._load_labels(results)
+ if self.with_mask:
+ results = self._load_masks(results)
+ if self.with_seg:
+ results = self._load_semantic_seg(results)
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += ('(with_bbox={}, with_label={}, with_mask={},'
+ ' with_seg={})').format(self.with_bbox, self.with_label,
+ self.with_mask, self.with_seg)
+ return repr_str
+
+
+@PIPELINES.register_module
+class LoadProposals(object):
+
+ def __init__(self, num_max_proposals=None):
+ self.num_max_proposals = num_max_proposals
+
+ def __call__(self, results):
+ proposals = results['proposals']
+ if proposals.shape[1] not in (4, 5):
+ raise AssertionError(
+ 'proposals should have shapes (n, 4) or (n, 5), '
+ 'but found {}'.format(proposals.shape))
+ proposals = proposals[:, :4]
+
+ if self.num_max_proposals is not None:
+ proposals = proposals[:self.num_max_proposals]
+
+ if len(proposals) == 0:
+ proposals = np.array([0, 0, 0, 0], dtype=np.float32)
+ results['proposals'] = proposals
+ results['bbox_fields'].append('proposals')
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(num_max_proposals={})'.format(
+ self.num_max_proposals)
diff --git a/mmdet/datasets/pipelines/test_aug.py b/mmdet/datasets/pipelines/test_aug.py
new file mode 100644
index 0000000000000000000000000000000000000000..b5d21807529bdda7f5a3f575cfd245c580cf7592
--- /dev/null
+++ b/mmdet/datasets/pipelines/test_aug.py
@@ -0,0 +1,38 @@
+import mmcv
+
+from ..registry import PIPELINES
+from .compose import Compose
+
+
+@PIPELINES.register_module
+class MultiScaleFlipAug(object):
+
+ def __init__(self, transforms, img_scale, flip=False):
+ self.transforms = Compose(transforms)
+ self.img_scale = img_scale if isinstance(img_scale,
+ list) else [img_scale]
+ assert mmcv.is_list_of(self.img_scale, tuple)
+ self.flip = flip
+
+ def __call__(self, results):
+ aug_data = []
+ flip_aug = [False, True] if self.flip else [False]
+ for scale in self.img_scale:
+ for flip in flip_aug:
+ _results = results.copy()
+ _results['scale'] = scale
+ _results['flip'] = flip
+ data = self.transforms(_results)
+ aug_data.append(data)
+ # list of dict to dict of list
+ aug_data_dict = {key: [] for key in aug_data[0]}
+ for data in aug_data:
+ for key, val in data.items():
+ aug_data_dict[key].append(val)
+ return aug_data_dict
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += '(transforms={}, img_scale={}, flip={})'.format(
+ self.transforms, self.img_scale, self.flip)
+ return repr_str
diff --git a/mmdet/datasets/pipelines/transforms.py b/mmdet/datasets/pipelines/transforms.py
new file mode 100644
index 0000000000000000000000000000000000000000..60ee42de69cd85845ea9ac8731a8d12bda7db715
--- /dev/null
+++ b/mmdet/datasets/pipelines/transforms.py
@@ -0,0 +1,634 @@
+import mmcv
+import numpy as np
+from imagecorruptions import corrupt
+from numpy import random
+
+from mmdet.core.evaluation.bbox_overlaps import bbox_overlaps
+from ..registry import PIPELINES
+
+
+@PIPELINES.register_module
+class Resize(object):
+ """Resize images & bbox & mask.
+
+ This transform resizes the input image to some scale. Bboxes and masks are
+ then resized with the same scale factor. If the input dict contains the key
+ "scale", then the scale in the input dict is used, otherwise the specified
+ scale in the init method is used.
+
+ `img_scale` can either be a tuple (single-scale) or a list of tuple
+ (multi-scale). There are 3 multiscale modes:
+ - `ratio_range` is not None: randomly sample a ratio from the ratio range
+ and multiply it with the image scale.
+ - `ratio_range` is None and `multiscale_mode` == "range": randomly sample a
+ scale from the a range.
+ - `ratio_range` is None and `multiscale_mode` == "value": randomly sample a
+ scale from multiple scales.
+
+ Args:
+ img_scale (tuple or list[tuple]): Images scales for resizing.
+ multiscale_mode (str): Either "range" or "value".
+ ratio_range (tuple[float]): (min_ratio, max_ratio)
+ keep_ratio (bool): Whether to keep the aspect ratio when resizing the
+ image.
+ """
+
+ def __init__(self,
+ img_scale=None,
+ multiscale_mode='range',
+ ratio_range=None,
+ keep_ratio=True):
+ if img_scale is None:
+ self.img_scale = None
+ else:
+ if isinstance(img_scale, list):
+ self.img_scale = img_scale
+ else:
+ self.img_scale = [img_scale]
+ assert mmcv.is_list_of(self.img_scale, tuple)
+
+ if ratio_range is not None:
+ # mode 1: given a scale and a range of image ratio
+ assert len(self.img_scale) == 1
+ else:
+ # mode 2: given multiple scales or a range of scales
+ assert multiscale_mode in ['value', 'range']
+
+ self.multiscale_mode = multiscale_mode
+ self.ratio_range = ratio_range
+ self.keep_ratio = keep_ratio
+
+ @staticmethod
+ def random_select(img_scales):
+ assert mmcv.is_list_of(img_scales, tuple)
+ scale_idx = np.random.randint(len(img_scales))
+ img_scale = img_scales[scale_idx]
+ return img_scale, scale_idx
+
+ @staticmethod
+ def random_sample(img_scales):
+ assert mmcv.is_list_of(img_scales, tuple) and len(img_scales) == 2
+ img_scale_long = [max(s) for s in img_scales]
+ img_scale_short = [min(s) for s in img_scales]
+ long_edge = np.random.randint(
+ min(img_scale_long),
+ max(img_scale_long) + 1)
+ short_edge = np.random.randint(
+ min(img_scale_short),
+ max(img_scale_short) + 1)
+ img_scale = (long_edge, short_edge)
+ return img_scale, None
+
+ @staticmethod
+ def random_sample_ratio(img_scale, ratio_range):
+ assert isinstance(img_scale, tuple) and len(img_scale) == 2
+ min_ratio, max_ratio = ratio_range
+ assert min_ratio <= max_ratio
+ ratio = np.random.random_sample() * (max_ratio - min_ratio) + min_ratio
+ scale = int(img_scale[0] * ratio), int(img_scale[1] * ratio)
+ return scale, None
+
+ def _random_scale(self, results):
+ if self.ratio_range is not None:
+ scale, scale_idx = self.random_sample_ratio(
+ self.img_scale[0], self.ratio_range)
+ elif len(self.img_scale) == 1:
+ scale, scale_idx = self.img_scale[0], 0
+ elif self.multiscale_mode == 'range':
+ scale, scale_idx = self.random_sample(self.img_scale)
+ elif self.multiscale_mode == 'value':
+ scale, scale_idx = self.random_select(self.img_scale)
+ else:
+ raise NotImplementedError
+
+ results['scale'] = scale
+ results['scale_idx'] = scale_idx
+
+ def _resize_img(self, results):
+ if self.keep_ratio:
+ img, scale_factor = mmcv.imrescale(
+ results['img'], results['scale'], return_scale=True)
+ else:
+ img, w_scale, h_scale = mmcv.imresize(
+ results['img'], results['scale'], return_scale=True)
+ scale_factor = np.array([w_scale, h_scale, w_scale, h_scale],
+ dtype=np.float32)
+ results['img'] = img
+ results['img_shape'] = img.shape
+ results['pad_shape'] = img.shape # in case that there is no padding
+ results['scale_factor'] = scale_factor
+ results['keep_ratio'] = self.keep_ratio
+
+ def _resize_bboxes(self, results):
+ img_shape = results['img_shape']
+ for key in results.get('bbox_fields', []):
+ bboxes = results[key] * results['scale_factor']
+ bboxes[:, 0::2] = np.clip(bboxes[:, 0::2], 0, img_shape[1] - 1)
+ bboxes[:, 1::2] = np.clip(bboxes[:, 1::2], 0, img_shape[0] - 1)
+ results[key] = bboxes
+
+ def _resize_masks(self, results):
+ for key in results.get('mask_fields', []):
+ if results[key] is None:
+ continue
+ if self.keep_ratio:
+ masks = [
+ mmcv.imrescale(
+ mask, results['scale_factor'], interpolation='nearest')
+ for mask in results[key]
+ ]
+ else:
+ mask_size = (results['img_shape'][1], results['img_shape'][0])
+ masks = [
+ mmcv.imresize(mask, mask_size, interpolation='nearest')
+ for mask in results[key]
+ ]
+ results[key] = masks
+
+ def __call__(self, results):
+ if 'scale' not in results:
+ self._random_scale(results)
+ self._resize_img(results)
+ self._resize_bboxes(results)
+ self._resize_masks(results)
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += ('(img_scale={}, multiscale_mode={}, ratio_range={}, '
+ 'keep_ratio={})').format(self.img_scale,
+ self.multiscale_mode,
+ self.ratio_range,
+ self.keep_ratio)
+ return repr_str
+
+
+@PIPELINES.register_module
+class RandomFlip(object):
+ """Flip the image & bbox & mask.
+
+ If the input dict contains the key "flip", then the flag will be used,
+ otherwise it will be randomly decided by a ratio specified in the init
+ method.
+
+ Args:
+ flip_ratio (float, optional): The flipping probability.
+ """
+
+ def __init__(self, flip_ratio=None):
+ self.flip_ratio = flip_ratio
+ if flip_ratio is not None:
+ assert flip_ratio >= 0 and flip_ratio <= 1
+
+ def bbox_flip(self, bboxes, img_shape):
+ """Flip bboxes horizontally.
+
+ Args:
+ bboxes(ndarray): shape (..., 4*k)
+ img_shape(tuple): (height, width)
+ """
+ assert bboxes.shape[-1] % 4 == 0
+ w = img_shape[1]
+ flipped = bboxes.copy()
+ flipped[..., 0::4] = w - bboxes[..., 2::4] - 1
+ flipped[..., 2::4] = w - bboxes[..., 0::4] - 1
+ return flipped
+
+ def __call__(self, results):
+ if 'flip' not in results:
+ flip = True if np.random.rand() < self.flip_ratio else False
+ results['flip'] = flip
+ if results['flip']:
+ # flip image
+ results['img'] = mmcv.imflip(results['img'])
+ # flip bboxes
+ for key in results.get('bbox_fields', []):
+ results[key] = self.bbox_flip(results[key],
+ results['img_shape'])
+ # flip masks
+ for key in results.get('mask_fields', []):
+ results[key] = [mask[:, ::-1] for mask in results[key]]
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(flip_ratio={})'.format(
+ self.flip_ratio)
+
+
+@PIPELINES.register_module
+class Pad(object):
+ """Pad the image & mask.
+
+ There are two padding modes: (1) pad to a fixed size and (2) pad to the
+ minimum size that is divisible by some number.
+
+ Args:
+ size (tuple, optional): Fixed padding size.
+ size_divisor (int, optional): The divisor of padded size.
+ pad_val (float, optional): Padding value, 0 by default.
+ """
+
+ def __init__(self, size=None, size_divisor=None, pad_val=0):
+ self.size = size
+ self.size_divisor = size_divisor
+ self.pad_val = pad_val
+ # only one of size and size_divisor should be valid
+ assert size is not None or size_divisor is not None
+ assert size is None or size_divisor is None
+
+ def _pad_img(self, results):
+ if self.size is not None:
+ padded_img = mmcv.impad(results['img'], self.size)
+ elif self.size_divisor is not None:
+ padded_img = mmcv.impad_to_multiple(
+ results['img'], self.size_divisor, pad_val=self.pad_val)
+ results['img'] = padded_img
+ results['pad_shape'] = padded_img.shape
+ results['pad_fixed_size'] = self.size
+ results['pad_size_divisor'] = self.size_divisor
+
+ def _pad_masks(self, results):
+ pad_shape = results['pad_shape'][:2]
+ for key in results.get('mask_fields', []):
+ padded_masks = [
+ mmcv.impad(mask, pad_shape, pad_val=self.pad_val)
+ for mask in results[key]
+ ]
+ results[key] = np.stack(padded_masks, axis=0)
+
+ def __call__(self, results):
+ self._pad_img(results)
+ self._pad_masks(results)
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += '(size={}, size_divisor={}, pad_val={})'.format(
+ self.size, self.size_divisor, self.pad_val)
+ return repr_str
+
+
+@PIPELINES.register_module
+class Normalize(object):
+ """Normalize the image.
+
+ Args:
+ mean (sequence): Mean values of 3 channels.
+ std (sequence): Std values of 3 channels.
+ to_rgb (bool): Whether to convert the image from BGR to RGB,
+ default is true.
+ """
+
+ def __init__(self, mean, std, to_rgb=True):
+ self.mean = np.array(mean, dtype=np.float32)
+ self.std = np.array(std, dtype=np.float32)
+ self.to_rgb = to_rgb
+
+ def __call__(self, results):
+ results['img'] = mmcv.imnormalize(results['img'], self.mean, self.std,
+ self.to_rgb)
+ results['img_norm_cfg'] = dict(
+ mean=self.mean, std=self.std, to_rgb=self.to_rgb)
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += '(mean={}, std={}, to_rgb={})'.format(
+ self.mean, self.std, self.to_rgb)
+ return repr_str
+
+
+@PIPELINES.register_module
+class RandomCrop(object):
+ """Random crop the image & bboxes.
+
+ Args:
+ crop_size (tuple): Expected size after cropping, (h, w).
+ """
+
+ def __init__(self, crop_size):
+ self.crop_size = crop_size
+
+ def __call__(self, results):
+ img = results['img']
+ margin_h = max(img.shape[0] - self.crop_size[0], 0)
+ margin_w = max(img.shape[1] - self.crop_size[1], 0)
+ offset_h = np.random.randint(0, margin_h + 1)
+ offset_w = np.random.randint(0, margin_w + 1)
+ crop_y1, crop_y2 = offset_h, offset_h + self.crop_size[0]
+ crop_x1, crop_x2 = offset_w, offset_w + self.crop_size[1]
+
+ # crop the image
+ img = img[crop_y1:crop_y2, crop_x1:crop_x2, :]
+ img_shape = img.shape
+ results['img'] = img
+ results['img_shape'] = img_shape
+
+ # crop bboxes accordingly and clip to the image boundary
+ for key in results.get('bbox_fields', []):
+ bbox_offset = np.array([offset_w, offset_h, offset_w, offset_h],
+ dtype=np.float32)
+ bboxes = results[key] - bbox_offset
+ bboxes[:, 0::2] = np.clip(bboxes[:, 0::2], 0, img_shape[1] - 1)
+ bboxes[:, 1::2] = np.clip(bboxes[:, 1::2], 0, img_shape[0] - 1)
+ results[key] = bboxes
+
+ # filter out the gt bboxes that are completely cropped
+ if 'gt_bboxes' in results:
+ gt_bboxes = results['gt_bboxes']
+ valid_inds = (gt_bboxes[:, 2] > gt_bboxes[:, 0]) & (
+ gt_bboxes[:, 3] > gt_bboxes[:, 1])
+ # if no gt bbox remains after cropping, just skip this image
+ if not np.any(valid_inds):
+ return None
+ results['gt_bboxes'] = gt_bboxes[valid_inds, :]
+ if 'gt_labels' in results:
+ results['gt_labels'] = results['gt_labels'][valid_inds]
+
+ # filter and crop the masks
+ if 'gt_masks' in results:
+ valid_gt_masks = []
+ for i in valid_inds:
+ gt_mask = results['gt_masks'][i][crop_y1:crop_y2, crop_x1:
+ crop_x2]
+ valid_gt_masks.append(gt_mask)
+ results['gt_masks'] = valid_gt_masks
+
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(crop_size={})'.format(
+ self.crop_size)
+
+
+@PIPELINES.register_module
+class SegResizeFlipPadRescale(object):
+ """A sequential transforms to semantic segmentation maps.
+
+ The same pipeline as input images is applied to the semantic segmentation
+ map, and finally rescale it by some scale factor. The transforms include:
+ 1. resize
+ 2. flip
+ 3. pad
+ 4. rescale (so that the final size can be different from the image size)
+
+ Args:
+ scale_factor (float): The scale factor of the final output.
+ """
+
+ def __init__(self, scale_factor=1):
+ self.scale_factor = scale_factor
+
+ def __call__(self, results):
+ if results['keep_ratio']:
+ gt_seg = mmcv.imrescale(
+ results['gt_semantic_seg'],
+ results['scale'],
+ interpolation='nearest')
+ else:
+ gt_seg = mmcv.imresize(
+ results['gt_semantic_seg'],
+ results['scale'],
+ interpolation='nearest')
+ if results['flip']:
+ gt_seg = mmcv.imflip(gt_seg)
+ if gt_seg.shape != results['pad_shape']:
+ gt_seg = mmcv.impad(gt_seg, results['pad_shape'][:2])
+ if self.scale_factor != 1:
+ gt_seg = mmcv.imrescale(
+ gt_seg, self.scale_factor, interpolation='nearest')
+ results['gt_semantic_seg'] = gt_seg
+ return results
+
+ def __repr__(self):
+ return self.__class__.__name__ + '(scale_factor={})'.format(
+ self.scale_factor)
+
+
+@PIPELINES.register_module
+class PhotoMetricDistortion(object):
+ """Apply photometric distortion to image sequentially, every transformation
+ is applied with a probability of 0.5. The position of random contrast is in
+ second or second to last.
+
+ 1. random brightness
+ 2. random contrast (mode 0)
+ 3. convert color from BGR to HSV
+ 4. random saturation
+ 5. random hue
+ 6. convert color from HSV to BGR
+ 7. random contrast (mode 1)
+ 8. randomly swap channels
+
+ Args:
+ brightness_delta (int): delta of brightness.
+ contrast_range (tuple): range of contrast.
+ saturation_range (tuple): range of saturation.
+ hue_delta (int): delta of hue.
+ """
+
+ def __init__(self,
+ brightness_delta=32,
+ contrast_range=(0.5, 1.5),
+ saturation_range=(0.5, 1.5),
+ hue_delta=18):
+ self.brightness_delta = brightness_delta
+ self.contrast_lower, self.contrast_upper = contrast_range
+ self.saturation_lower, self.saturation_upper = saturation_range
+ self.hue_delta = hue_delta
+
+ def __call__(self, results):
+ img = results['img']
+ # random brightness
+ if random.randint(2):
+ delta = random.uniform(-self.brightness_delta,
+ self.brightness_delta)
+ img += delta
+
+ # mode == 0 --> do random contrast first
+ # mode == 1 --> do random contrast last
+ mode = random.randint(2)
+ if mode == 1:
+ if random.randint(2):
+ alpha = random.uniform(self.contrast_lower,
+ self.contrast_upper)
+ img *= alpha
+
+ # convert color from BGR to HSV
+ img = mmcv.bgr2hsv(img)
+
+ # random saturation
+ if random.randint(2):
+ img[..., 1] *= random.uniform(self.saturation_lower,
+ self.saturation_upper)
+
+ # random hue
+ if random.randint(2):
+ img[..., 0] += random.uniform(-self.hue_delta, self.hue_delta)
+ img[..., 0][img[..., 0] > 360] -= 360
+ img[..., 0][img[..., 0] < 0] += 360
+
+ # convert color from HSV to BGR
+ img = mmcv.hsv2bgr(img)
+
+ # random contrast
+ if mode == 0:
+ if random.randint(2):
+ alpha = random.uniform(self.contrast_lower,
+ self.contrast_upper)
+ img *= alpha
+
+ # randomly swap channels
+ if random.randint(2):
+ img = img[..., random.permutation(3)]
+
+ results['img'] = img
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += ('(brightness_delta={}, contrast_range={}, '
+ 'saturation_range={}, hue_delta={})').format(
+ self.brightness_delta, self.contrast_range,
+ self.saturation_range, self.hue_delta)
+ return repr_str
+
+
+@PIPELINES.register_module
+class Expand(object):
+ """Random expand the image & bboxes.
+
+ Randomly place the original image on a canvas of 'ratio' x original image
+ size filled with mean values. The ratio is in the range of ratio_range.
+
+ Args:
+ mean (tuple): mean value of dataset.
+ to_rgb (bool): if need to convert the order of mean to align with RGB.
+ ratio_range (tuple): range of expand ratio.
+ """
+
+ def __init__(self, mean=(0, 0, 0), to_rgb=True, ratio_range=(1, 4)):
+ if to_rgb:
+ self.mean = mean[::-1]
+ else:
+ self.mean = mean
+ self.min_ratio, self.max_ratio = ratio_range
+
+ def __call__(self, results):
+ if random.randint(2):
+ return results
+
+ img, boxes = [results[k] for k in ('img', 'gt_bboxes')]
+
+ h, w, c = img.shape
+ ratio = random.uniform(self.min_ratio, self.max_ratio)
+ expand_img = np.full((int(h * ratio), int(w * ratio), c),
+ self.mean).astype(img.dtype)
+ left = int(random.uniform(0, w * ratio - w))
+ top = int(random.uniform(0, h * ratio - h))
+ expand_img[top:top + h, left:left + w] = img
+ boxes += np.tile((left, top), 2)
+
+ results['img'] = expand_img
+ results['gt_bboxes'] = boxes
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += '(mean={}, to_rgb={}, ratio_range={})'.format(
+ self.mean, self.to_rgb, self.ratio_range)
+ return repr_str
+
+
+@PIPELINES.register_module
+class MinIoURandomCrop(object):
+ """Random crop the image & bboxes, the cropped patches have minimum IoU
+ requirement with original image & bboxes, the IoU threshold is randomly
+ selected from min_ious.
+
+ Args:
+ min_ious (tuple): minimum IoU threshold
+ crop_size (tuple): Expected size after cropping, (h, w).
+ """
+
+ def __init__(self, min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3):
+ # 1: return ori img
+ self.sample_mode = (1, *min_ious, 0)
+ self.min_crop_size = min_crop_size
+
+ def __call__(self, results):
+ img, boxes, labels = [
+ results[k] for k in ('img', 'gt_bboxes', 'gt_labels')
+ ]
+ h, w, c = img.shape
+ while True:
+ mode = random.choice(self.sample_mode)
+ if mode == 1:
+ return results
+
+ min_iou = mode
+ for i in range(50):
+ new_w = random.uniform(self.min_crop_size * w, w)
+ new_h = random.uniform(self.min_crop_size * h, h)
+
+ # h / w in [0.5, 2]
+ if new_h / new_w < 0.5 or new_h / new_w > 2:
+ continue
+
+ left = random.uniform(w - new_w)
+ top = random.uniform(h - new_h)
+
+ patch = np.array(
+ (int(left), int(top), int(left + new_w), int(top + new_h)))
+ overlaps = bbox_overlaps(
+ patch.reshape(-1, 4), boxes.reshape(-1, 4)).reshape(-1)
+ if overlaps.min() < min_iou:
+ continue
+
+ # center of boxes should inside the crop img
+ center = (boxes[:, :2] + boxes[:, 2:]) / 2
+ mask = (center[:, 0] > patch[0]) * (
+ center[:, 1] > patch[1]) * (center[:, 0] < patch[2]) * (
+ center[:, 1] < patch[3])
+ if not mask.any():
+ continue
+ boxes = boxes[mask]
+ labels = labels[mask]
+
+ # adjust boxes
+ img = img[patch[1]:patch[3], patch[0]:patch[2]]
+ boxes[:, 2:] = boxes[:, 2:].clip(max=patch[2:])
+ boxes[:, :2] = boxes[:, :2].clip(min=patch[:2])
+ boxes -= np.tile(patch[:2], 2)
+
+ results['img'] = img
+ results['gt_bboxes'] = boxes
+ results['gt_labels'] = labels
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += '(min_ious={}, min_crop_size={})'.format(
+ self.min_ious, self.min_crop_size)
+ return repr_str
+
+
+@PIPELINES.register_module
+class Corrupt(object):
+
+ def __init__(self, corruption, severity=1):
+ self.corruption = corruption
+ self.severity = severity
+
+ def __call__(self, results):
+ results['img'] = corrupt(
+ results['img'].astype(np.uint8),
+ corruption_name=self.corruption,
+ severity=self.severity)
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += '(corruption={}, severity={})'.format(
+ self.corruption, self.severity)
+ return repr_str
diff --git a/mmdet/datasets/registry.py b/mmdet/datasets/registry.py
index e7266240be5cd15fd505be335e12a0fb7d67dd31..974a4fbb769fe70770fa7d41766f9ce041244195 100644
--- a/mmdet/datasets/registry.py
+++ b/mmdet/datasets/registry.py
@@ -1,3 +1,4 @@
from mmdet.utils import Registry
DATASETS = Registry('dataset')
+PIPELINES = Registry('pipeline')
diff --git a/mmdet/datasets/utils.py b/mmdet/datasets/utils.py
deleted file mode 100644
index 9f4f46caec7d2411da44eda8f41ae48fdf881e00..0000000000000000000000000000000000000000
--- a/mmdet/datasets/utils.py
+++ /dev/null
@@ -1,68 +0,0 @@
-from collections import Sequence
-
-import matplotlib.pyplot as plt
-import mmcv
-import numpy as np
-import torch
-
-
-def to_tensor(data):
- """Convert objects of various python types to :obj:`torch.Tensor`.
-
- Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
- :class:`Sequence`, :class:`int` and :class:`float`.
- """
- if isinstance(data, torch.Tensor):
- return data
- elif isinstance(data, np.ndarray):
- return torch.from_numpy(data)
- elif isinstance(data, Sequence) and not mmcv.is_str(data):
- return torch.tensor(data)
- elif isinstance(data, int):
- return torch.LongTensor([data])
- elif isinstance(data, float):
- return torch.FloatTensor([data])
- else:
- raise TypeError('type {} cannot be converted to tensor.'.format(
- type(data)))
-
-
-def random_scale(img_scales, mode='range'):
- """Randomly select a scale from a list of scales or scale ranges.
-
- Args:
- img_scales (list[tuple]): Image scale or scale range.
- mode (str): "range" or "value".
-
- Returns:
- tuple: Sampled image scale.
- """
- num_scales = len(img_scales)
- if num_scales == 1: # fixed scale is specified
- img_scale = img_scales[0]
- elif num_scales == 2: # randomly sample a scale
- if mode == 'range':
- img_scale_long = [max(s) for s in img_scales]
- img_scale_short = [min(s) for s in img_scales]
- long_edge = np.random.randint(
- min(img_scale_long),
- max(img_scale_long) + 1)
- short_edge = np.random.randint(
- min(img_scale_short),
- max(img_scale_short) + 1)
- img_scale = (long_edge, short_edge)
- elif mode == 'value':
- img_scale = img_scales[np.random.randint(num_scales)]
- else:
- if mode != 'value':
- raise ValueError(
- 'Only "value" mode supports more than 2 image scales')
- img_scale = img_scales[np.random.randint(num_scales)]
- return img_scale
-
-
-def show_ann(coco, img, ann_info):
- plt.imshow(mmcv.bgr2rgb(img))
- plt.axis('off')
- coco.showAnns(ann_info)
- plt.show()
diff --git a/mmdet/models/detectors/base.py b/mmdet/models/detectors/base.py
index 038dd109c08a454d4505616a3c7c8eb9ffe0580e..7650878b6d63204d6974b0a46c23f079d0bd5a4b 100644
--- a/mmdet/models/detectors/base.py
+++ b/mmdet/models/detectors/base.py
@@ -87,12 +87,7 @@ class BaseDetector(nn.Module):
else:
return self.forward_test(img, img_meta, **kwargs)
- def show_result(self,
- data,
- result,
- img_norm_cfg,
- dataset=None,
- score_thr=0.3):
+ def show_result(self, data, result, dataset=None, score_thr=0.3):
if isinstance(result, tuple):
bbox_result, segm_result = result
else:
@@ -100,7 +95,7 @@ class BaseDetector(nn.Module):
img_tensor = data['img'][0]
img_metas = data['img_meta'][0].data[0]
- imgs = tensor2imgs(img_tensor, **img_norm_cfg)
+ imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
assert len(imgs) == len(img_metas)
if dataset is None:
diff --git a/mmdet/models/detectors/cascade_rcnn.py b/mmdet/models/detectors/cascade_rcnn.py
index bd878eb40c0bcfd126cf8e3a62a6ef8a1bf86cf5..4333b811bdeee15984f752804ffeeae77ffb38b3 100644
--- a/mmdet/models/detectors/cascade_rcnn.py
+++ b/mmdet/models/detectors/cascade_rcnn.py
@@ -402,7 +402,7 @@ class CascadeRCNN(BaseDetector, RPNTestMixin):
def aug_test(self, img, img_meta, proposals=None, rescale=False):
raise NotImplementedError
- def show_result(self, data, result, img_norm_cfg, **kwargs):
+ def show_result(self, data, result, **kwargs):
if self.with_mask:
ms_bbox_result, ms_segm_result = result
if isinstance(ms_bbox_result, dict):
@@ -411,5 +411,4 @@ class CascadeRCNN(BaseDetector, RPNTestMixin):
else:
if isinstance(result, dict):
result = result['ensemble']
- super(CascadeRCNN, self).show_result(data, result, img_norm_cfg,
- **kwargs)
+ super(CascadeRCNN, self).show_result(data, result, **kwargs)
diff --git a/mmdet/models/detectors/rpn.py b/mmdet/models/detectors/rpn.py
index c9de290fbfa46b3daeb8a062ed0f582b67dc147a..fafee4fc21f58ada5a02d9e91a1685b0dadb2474 100644
--- a/mmdet/models/detectors/rpn.py
+++ b/mmdet/models/detectors/rpn.py
@@ -81,7 +81,7 @@ class RPN(BaseDetector, RPNTestMixin):
# TODO: remove this restriction
return proposal_list[0].cpu().numpy()
- def show_result(self, data, result, img_norm_cfg, dataset=None, top_k=20):
+ def show_result(self, data, result, dataset=None, top_k=20):
"""Show RPN proposals on the image.
Although we assume batch size is 1, this method supports arbitrary
@@ -89,7 +89,7 @@ class RPN(BaseDetector, RPNTestMixin):
"""
img_tensor = data['img'][0]
img_metas = data['img_meta'][0].data[0]
- imgs = tensor2imgs(img_tensor, **img_norm_cfg)
+ imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
assert len(imgs) == len(img_metas)
for img, img_meta in zip(imgs, img_metas):
h, w, _ = img_meta['img_shape']
diff --git a/mmdet/utils/registry.py b/mmdet/utils/registry.py
index e39552a844bf5f37c19b95750c38a612a33bc15e..a1cc87dcfdb5d954ec6fa496b4ffc52ac14dbbfa 100644
--- a/mmdet/utils/registry.py
+++ b/mmdet/utils/registry.py
@@ -61,14 +61,16 @@ def build_from_cfg(cfg, registry, default_args=None):
args = cfg.copy()
obj_type = args.pop('type')
if mmcv.is_str(obj_type):
- obj_type = registry.get(obj_type)
- if obj_type is None:
+ obj_cls = registry.get(obj_type)
+ if obj_cls is None:
raise KeyError('{} is not in the {} registry'.format(
obj_type, registry.name))
- elif not inspect.isclass(obj_type):
+ elif inspect.isclass(obj_type):
+ obj_cls = obj_type
+ else:
raise TypeError('type must be a str or valid type, but got {}'.format(
type(obj_type)))
if default_args is not None:
for name, value in default_args.items():
args.setdefault(name, value)
- return obj_type(**args)
+ return obj_cls(**args)
diff --git a/tools/test.py b/tools/test.py
index c0fdec700ca63b3f68f78187ad1f0ec4d3021db2..e3ff48734e35cffaef17f575c68ef5bc07ac5b3b 100644
--- a/tools/test.py
+++ b/tools/test.py
@@ -27,7 +27,7 @@ def single_gpu_test(model, data_loader, show=False):
results.append(result)
if show:
- model.module.show_result(data, result, dataset.img_norm_cfg)
+ model.module.show_result(data, result)
batch_size = data['img'][0].size(0)
for _ in range(batch_size):
diff --git a/tools/test_robustness.py b/tools/test_robustness.py
index 584654b618bef768dfe15204caedaecb68b2c9ea..e2632151777b32a83aedf198c3db4796b57e65ca 100644
--- a/tools/test_robustness.py
+++ b/tools/test_robustness.py
@@ -1,4 +1,5 @@
import argparse
+import copy
import os
import os.path as osp
import shutil
@@ -350,13 +351,15 @@ def main():
continue
# assign corruption and severity
- if corruption_severity == 0:
- # evaluate without corruptions for severity = 0
- cfg.data.test['corruption'] = None
- cfg.data.test['corruption_severity'] = 0
- else:
- cfg.data.test['corruption'] = corruption
- cfg.data.test['corruption_severity'] = corruption_severity
+ if corruption_severity > 0:
+ test_data_cfg = copy.deepcopy(cfg.data.test)
+ corruption_trans = dict(
+ type='Corrupt',
+ corruption=corruption,
+ severity=corruption_severity)
+ # TODO: hard coded "1", we assume that the first step is
+ # loading images, which needs to be fixed in the future
+ test_data_cfg['pipeline'].insert(1, corruption_trans)
# print info
print('\nTesting {} at severity {}'.format(corruption,