Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found

Target

Select target project
  • Archana_Badagi/food-round2
  • eric_a_scuccimarra/food-round2
  • joel_joseph/food-round2
  • darthgera123/food-round2
  • reshmarameshbabu/food-round2
  • nikhil_rayaprolu/food-round2
6 results
Show changes
Hide whitespace changes
Inline Side-by-side
Showing
with 1257 additions and 545 deletions
configs/albu_example/mask_rcnn_r50_fpn_1x.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
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),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
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)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
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,
mask_thr_binary=0.5))
# 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)
albu_train_transforms = [
dict(
type='ShiftScaleRotate',
shift_limit=0.0625,
scale_limit=0.0,
rotate_limit=0,
interpolation=1,
p=0.5),
dict(
type='RandomBrightnessContrast',
brightness_limit=[0.1, 0.3],
contrast_limit=[0.1, 0.3],
p=0.2),
dict(
type='OneOf',
transforms=[
dict(
type='RGBShift',
r_shift_limit=10,
g_shift_limit=10,
b_shift_limit=10,
p=1.0),
dict(
type='HueSaturationValue',
hue_shift_limit=20,
sat_shift_limit=30,
val_shift_limit=20,
p=1.0)
],
p=0.1),
dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
dict(type='ChannelShuffle', p=0.1),
dict(
type='OneOf',
transforms=[
dict(type='Blur', blur_limit=3, p=1.0),
dict(type='MedianBlur', blur_limit=3, p=1.0)
],
p=0.1),
]
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='Pad', size_divisor=32),
dict(
type='Albu',
transforms=albu_train_transforms,
bbox_params=dict(
type='BboxParams',
format='pascal_voc',
label_fields=['gt_labels'],
min_visibility=0.0,
filter_lost_elements=True),
keymap={
'img': 'image',
'gt_masks': 'masks',
'gt_bboxes': 'bboxes'
},
update_pad_shape=False,
skip_img_without_anno=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor'))
]
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,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
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/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
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))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
evaluation = dict(interval=1)
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/atss/README.md 0 → 100644
View file @ 49243848
# Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
## Introduction
```
@article{zhang2019bridging,
title = {Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection},
author = {Zhang, Shifeng and Chi, Cheng and Yao, Yongqiang and Lei, Zhen and Li, Stan Z.},
journal = {arXiv preprint arXiv:1912.02424},
year = {2019}
}
```
## Results and Models
| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
|:---------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
| R-50 | pytorch | 1x | 3.6 | 0.357 | 12.8 | 39.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/atss/atss_r50_fpn_1x_20200113-a7aa251e.pth)|
configs/atss/atss_r50_fpn_1x.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='ATSS',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
extra_convs_on_inputs=False,
num_outs=5),
bbox_head=dict(
type='ATSSHead',
num_classes=81,
in_channels=256,
stacked_convs=4,
feat_channels=256,
octave_base_scale=8,
scales_per_octave=1,
anchor_ratios=[1.0],
anchor_strides=[8, 16, 32, 64, 128],
target_means=[.0, .0, .0, .0],
target_stds=[0.1, 0.1, 0.2, 0.2],
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
loss_centerness=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)))
# training and testing settings
train_cfg = dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False)
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.6),
max_per_img=100)
# 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)
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,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
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/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
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))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/atss_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/cascade_mask_rcnn_r101_fpn_1x.py
View file @ 49243848
......@@ -2,7 +2,7 @@
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='modelzoo://resnet101',
pretrained='torchvision://resnet101',
backbone=dict(
type='ResNet',
depth=101,
......@@ -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',
......@@ -189,13 +174,37 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# 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)
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 +212,17 @@ 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))
......
configs/cascade_mask_rcnn_r50_caffe_c4_1x.py
View file @ 49243848
......@@ -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(
......@@ -191,49 +176,55 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# dataset settings
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))
......
configs/cascade_mask_rcnn_r50_fpn_1x.py
View file @ 49243848
......@@ -2,7 +2,7 @@
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='modelzoo://resnet50',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
......@@ -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',
......@@ -189,13 +174,37 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# 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)
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 +212,17 @@ 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))
......
configs/cascade_mask_rcnn_x101_32x4d_fpn_1x.py
View file @ 49243848
......@@ -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',
......@@ -191,13 +176,37 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# 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)
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 +214,17 @@ 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))
......
configs/cascade_mask_rcnn_x101_64x4d_fpn_1x.py
View file @ 49243848
......@@ -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',
......@@ -191,13 +176,37 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# 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)
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 +214,17 @@ 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))
......
configs/cascade_rcnn_r101_fpn_1x.py
View file @ 49243848
......@@ -2,7 +2,7 @@
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='modelzoo://resnet101',
pretrained='torchvision://resnet101',
backbone=dict(
type='ResNet',
depth=101,
......@@ -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(
......@@ -170,13 +155,37 @@ 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),
keep_all_stages=False)
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# 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)
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 +193,17 @@ 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))
......
configs/cascade_rcnn_r50_caffe_c4_1x.py
View file @ 49243848
......@@ -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(
......@@ -179,49 +164,55 @@ 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),
keep_all_stages=False)
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# dataset settings
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))
......
configs/cascade_rcnn_r50_fpn_1x.py
View file @ 49243848
......@@ -2,7 +2,7 @@
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='modelzoo://resnet50',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
......@@ -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(
......@@ -170,13 +155,37 @@ 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),
keep_all_stages=False)
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# 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)
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 +193,17 @@ 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))
......
configs/cascade_rcnn_x101_32x4d_fpn_1x.py
View file @ 49243848
......@@ -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(
......@@ -172,13 +157,37 @@ 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),
keep_all_stages=False)
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# 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)
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 +195,17 @@ 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))
......
configs/cascade_rcnn_x101_64x4d_fpn_1x.py
View file @ 49243848
......@@ -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(
......@@ -172,13 +157,37 @@ 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),
keep_all_stages=False)
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# 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)
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 +195,17 @@ 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))
......
configs/cityscapes/README.md 0 → 100644
View file @ 49243848
## Common settings
- All baselines were trained using 8 GPU with a batch size of 8 (1 images per GPU) using the [linear scaling rule](https://arxiv.org/abs/1706.02677) to scale the learning rate.
- All models were trained on `cityscapes_train`, and tested on `cityscapes_val`.
- 1x training schedule indicates 64 epochs which corresponds to slightly less than the 24k iterations reported in the original schedule from the [Mask R-CNN paper](https://arxiv.org/abs/1703.06870)
- All pytorch-style pretrained backbones on ImageNet are from PyTorch model zoo.
## Baselines
Download links and more models with different backbones and training schemes will be added to the model zoo.
### Faster R-CNN
| Backbone | Style | Lr schd | Scale | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
| :-------------: | :-----: | :-----: | :---: | :------: | :-----------------: | :------------: | :----: | :------: |
| R-50-FPN | pytorch | 1x | 800-1024 | 4.9 | 0.345 | 8.8 | 36.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/cityscapes/faster_rcnn_r50_fpn_1x_city_20190727-7b9c0534.pth) |
### Mask R-CNN
| Backbone | Style | Lr schd | Scale | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
| :-------------: | :-----: | :-----: | :------: | :------: | :-----------------: | :------------: | :----: | :-----: | :------: |
| R-50-FPN | pytorch | 1x | 800-1024 | 4.9 | 0.609 | 2.5 | 37.4 | 32.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/cityscapes/mask_rcnn_r50_fpn_1x_city_20190727-9b3c56a5.pth) |
**Notes:**
- In the original paper, the mask AP of Mask R-CNN R-50-FPN is 31.5.
configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='FasterRCNN',
pretrained='modelzoo://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
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),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=9,
target_means=[0., 0., 0., 0.],
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)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
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)
# soft-nms is also supported for rcnn testing
# e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
)
# dataset settings
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',
times=8,
dataset=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_train.json',
img_prefix=data_root + 'train/',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
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)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[6])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=100,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 8 # actual epoch = 8 * 8 = 64
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='MaskRCNN',
pretrained='modelzoo://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
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),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=9,
target_means=[0., 0., 0., 0.],
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)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=9,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
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,
mask_thr_binary=0.5))
# dataset settings
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',
times=8,
dataset=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_train.json',
img_prefix=data_root + 'train/',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'val/',
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)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[6])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=100,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 8 # actual epoch = 8 * 8 = 64
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/dcn/README.md
View file @ 49243848
......@@ -24,6 +24,7 @@
|:---------:|:------------:|:-------:|:-------------:|:------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
| R-50-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 3.9 | 0.594 | 10.2 | 40.0 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-e41688c9.pth) |
| R-50-FPN | Faster | pytorch | mdconv(c3-c5) | - | 1x | 3.7 | 0.598 | 10.0 | 40.2 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x_20190125-1b768045.pth) |
| *R-50-FPN (dg=4) | Faster | pytorch | mdconv(c3-c5) | - | 1x | 3.9 | 0.350 | 11.36 | 40.4 | - | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/dcn/faster_rcnn_mdconv_c3-c5_group4_r50_fpn_1x_20190911-5591a7e4.pth) |
| R-50-FPN | Faster | pytorch | - | dpool | 1x | 4.6 | 0.714 | 8.7 | 37.8 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dpool_r50_fpn_1x_20190125-f4fc1d70.pth) |
| R-50-FPN | Faster | pytorch | - | mdpool | 1x | 5.2 | 0.769 | 8.2 | 38.0 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_mdpool_r50_fpn_1x_20190125-473d0f3d.pth) |
| R-101-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 5.8 | 0.811 | 8.0 | 42.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-a7e31b65.pth) |
......@@ -40,4 +41,5 @@
- `dconv` and `mdconv` denote (modulated) deformable convolution, `c3-c5` means adding dconv in resnet stage 3 to 5. `dpool` and `mdpool` denote (modulated) deformable roi pooling.
- The dcn ops are modified from https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch, which should be more memory efficient and slightly faster.
- (*) For R-50-FPN (dg=4), dg is short for deformable_group. This model is trained and tested on Amazon EC2 p3dn.24xlarge instance.
- **Memory, Train/Inf time is outdated.**
\ No newline at end of file
configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
View file @ 49243848
......@@ -2,7 +2,7 @@
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='modelzoo://resnet50',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
......@@ -10,8 +10,7 @@ model = dict(
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(
modulated=False, deformable_groups=1, fallback_on_stride=False),
dcn=dict(type='DCN', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
......@@ -177,13 +176,37 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# 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)
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 +214,17 @@ 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))
......
configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py
View file @ 49243848
......@@ -2,7 +2,7 @@
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='modelzoo://resnet50',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
......@@ -10,10 +10,7 @@ model = dict(
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(
modulated=False,
deformable_groups=1,
fallback_on_stride=False),
dcn=dict(type='DCN', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
......@@ -49,13 +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,
......@@ -67,13 +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,
......@@ -85,13 +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(
......@@ -175,13 +157,37 @@ 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),
keep_all_stages=False)
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# 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)
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 +195,17 @@ 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))
......
configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py
View file @ 49243848
# model settings
model = dict(
type='FasterRCNN',
pretrained='modelzoo://resnet50',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
......@@ -9,8 +9,7 @@ model = dict(
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(
modulated=False, deformable_groups=1, fallback_on_stride=False),
dcn=dict(type='DCN', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
......@@ -105,6 +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,
......@@ -112,35 +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))
......