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 788 additions and 456 deletions
configs/dcn/mask_rcnn_mdconv_c3-c5_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',
dcn=dict(type='DCNv2', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
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)
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,
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
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_dconv_c3-c5_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/double_heads/dh_faster_rcnn_r50_fpn_1x.py
View file @ 49243848
...@@ -105,6 +105,31 @@ dataset_type = 'CocoDataset' ...@@ -105,6 +105,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -112,35 +137,17 @@ data = dict( ...@@ -112,35 +137,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FasterRCNN', type='FasterRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -106,6 +106,31 @@ dataset_type = 'CocoDataset' ...@@ -106,6 +106,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -113,35 +138,17 @@ data = dict( ...@@ -113,35 +138,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FasterRCNN', type='FasterRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -12,8 +12,7 @@ model = dict( ...@@ -12,8 +12,7 @@ model = dict(
gen_attention=dict( gen_attention=dict(
spatial_range=-1, num_heads=8, attention_type='0010', kv_stride=2), spatial_range=-1, num_heads=8, attention_type='0010', kv_stride=2),
stage_with_gen_attention=[[], [], [0, 1, 2, 3, 4, 5], [0, 1, 2]], stage_with_gen_attention=[[], [], [0, 1, 2, 3, 4, 5], [0, 1, 2]],
dcn=dict( dcn=dict(type='DCN', deformable_groups=1, fallback_on_stride=False),
modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True), stage_with_dcn=(False, True, True, True),
), ),
neck=dict( neck=dict(
...@@ -109,6 +108,31 @@ dataset_type = 'CocoDataset' ...@@ -109,6 +108,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -116,35 +140,17 @@ data = dict( ...@@ -116,35 +140,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FasterRCNN', type='FasterRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -106,6 +106,31 @@ dataset_type = 'CocoDataset' ...@@ -106,6 +106,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -113,35 +138,17 @@ data = dict( ...@@ -113,35 +138,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FasterRCNN', type='FasterRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -12,8 +12,7 @@ model = dict( ...@@ -12,8 +12,7 @@ model = dict(
gen_attention=dict( gen_attention=dict(
spatial_range=-1, num_heads=8, attention_type='1111', kv_stride=2), spatial_range=-1, num_heads=8, attention_type='1111', kv_stride=2),
stage_with_gen_attention=[[], [], [0, 1, 2, 3, 4, 5], [0, 1, 2]], stage_with_gen_attention=[[], [], [0, 1, 2, 3, 4, 5], [0, 1, 2]],
dcn=dict( dcn=dict(type='DCN', deformable_groups=1, fallback_on_stride=False),
modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True), stage_with_dcn=(False, True, True, True),
), ),
neck=dict( neck=dict(
...@@ -109,6 +108,31 @@ dataset_type = 'CocoDataset' ...@@ -109,6 +108,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -116,35 +140,17 @@ data = dict( ...@@ -116,35 +140,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/fast_mask_rcnn_r101_fpn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FastRCNN', type='FastRCNN',
pretrained='modelzoo://resnet101', pretrained='torchvision://resnet101',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=101, depth=101,
...@@ -74,45 +74,56 @@ dataset_type = 'CocoDataset' ...@@ -74,45 +74,56 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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='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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
train=dict( train=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
flip_ratio=0.5, img_prefix=data_root + 'train2017/',
with_mask=True, pipeline=train_pipeline),
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline),
with_mask=True,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline))
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/fast_mask_rcnn_r50_caffe_c4_1x.py
View file @ 49243848
...@@ -73,45 +73,56 @@ dataset_type = 'CocoDataset' ...@@ -73,45 +73,56 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False) 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( data = dict(
imgs_per_gpu=1, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
train=dict( train=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_c4_1x_train2017.pkl',
flip_ratio=0.5, img_prefix=data_root + 'train2017/',
with_mask=True, pipeline=train_pipeline),
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
flip_ratio=0, img_prefix=data_root + 'val2017/',
with_mask=True, pipeline=test_pipeline),
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
flip_ratio=0, img_prefix=data_root + 'val2017/',
with_mask=False, pipeline=test_pipeline))
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/fast_mask_rcnn_r50_fpn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FastRCNN', type='FastRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -74,45 +74,56 @@ dataset_type = 'CocoDataset' ...@@ -74,45 +74,56 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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='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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
train=dict( train=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
flip_ratio=0.5, img_prefix=data_root + 'train2017/',
with_mask=True, pipeline=train_pipeline),
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline),
with_mask=True,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline))
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/fast_rcnn_r101_fpn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FastRCNN', type='FastRCNN',
pretrained='modelzoo://resnet101', pretrained='torchvision://resnet101',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=101, depth=101,
...@@ -30,11 +30,8 @@ model = dict( ...@@ -30,11 +30,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2], target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False, reg_class_agnostic=False,
loss_cls=dict( loss_cls=dict(
type='CrossEntropyLoss', type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
use_sigmoid=False, loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
loss_weight=1.0),
loss_bbox=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings # model training and testing settings
train_cfg = dict( train_cfg = dict(
rcnn=dict( rcnn=dict(
...@@ -60,45 +57,54 @@ dataset_type = 'CocoDataset' ...@@ -60,45 +57,54 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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='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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
train=dict( train=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
flip_ratio=0.5, img_prefix=data_root + 'train2017/',
with_mask=False, pipeline=train_pipeline),
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline),
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline))
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/fast_rcnn_r50_caffe_c4_1x.py
View file @ 49243848
...@@ -38,11 +38,8 @@ model = dict( ...@@ -38,11 +38,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2], target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False, reg_class_agnostic=False,
loss_cls=dict( loss_cls=dict(
type='CrossEntropyLoss', type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
use_sigmoid=False, loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
loss_weight=1.0),
loss_bbox=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings # model training and testing settings
train_cfg = dict( train_cfg = dict(
rcnn=dict( rcnn=dict(
...@@ -68,45 +65,54 @@ dataset_type = 'CocoDataset' ...@@ -68,45 +65,54 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False) 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( data = dict(
imgs_per_gpu=1, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
train=dict( train=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_c4_1x_train2017.pkl',
flip_ratio=0.5, img_prefix=data_root + 'train2017/',
with_mask=False, pipeline=train_pipeline),
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
flip_ratio=0, img_prefix=data_root + 'val2017/',
with_mask=False, pipeline=test_pipeline),
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
flip_ratio=0, img_prefix=data_root + 'val2017/',
with_mask=False, pipeline=test_pipeline))
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/fast_rcnn_r50_fpn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FastRCNN', type='FastRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -30,11 +30,8 @@ model = dict( ...@@ -30,11 +30,8 @@ model = dict(
target_stds=[0.1, 0.1, 0.2, 0.2], target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False, reg_class_agnostic=False,
loss_cls=dict( loss_cls=dict(
type='CrossEntropyLoss', type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
use_sigmoid=False, loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
loss_weight=1.0),
loss_bbox=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings # model training and testing settings
train_cfg = dict( train_cfg = dict(
rcnn=dict( rcnn=dict(
...@@ -60,45 +57,54 @@ dataset_type = 'CocoDataset' ...@@ -60,45 +57,54 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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='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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
train=dict( train=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
flip_ratio=0.5, img_prefix=data_root + 'train2017/',
with_mask=False, pipeline=train_pipeline),
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline),
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', 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', proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
size_divisor=32, img_prefix=data_root + 'val2017/',
flip_ratio=0, pipeline=test_pipeline))
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/faster_rcnn_ohem_r50_fpn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FasterRCNN', type='FasterRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset' ...@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -109,35 +134,17 @@ data = dict( ...@@ -109,35 +134,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/faster_rcnn_r101_fpn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FasterRCNN', type='FasterRCNN',
pretrained='modelzoo://resnet101', pretrained='torchvision://resnet101',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=101, depth=101,
...@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset' ...@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -109,35 +134,17 @@ data = dict( ...@@ -109,35 +134,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/faster_rcnn_r50_caffe_c4_1x.py
View file @ 49243848
...@@ -107,42 +107,49 @@ dataset_type = 'CocoDataset' ...@@ -107,42 +107,49 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False) 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( data = dict(
imgs_per_gpu=1, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
train=dict( train=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/faster_rcnn_r50_fpn_1x.py
View file @ 49243848
# model settings # model settings
model = dict( model = dict(
type='FasterRCNN', type='FasterRCNN',
pretrained='modelzoo://resnet50', pretrained='torchvision://resnet50',
backbone=dict( backbone=dict(
type='ResNet', type='ResNet',
depth=50, depth=50,
...@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset' ...@@ -102,6 +102,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -109,35 +134,17 @@ data = dict( ...@@ -109,35 +134,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/faster_rcnn_x101_32x4d_fpn_1x.py
View file @ 49243848
...@@ -104,6 +104,31 @@ dataset_type = 'CocoDataset' ...@@ -104,6 +104,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -111,35 +136,17 @@ data = dict( ...@@ -111,35 +136,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/faster_rcnn_x101_64x4d_fpn_1x.py
View file @ 49243848
...@@ -104,6 +104,31 @@ dataset_type = 'CocoDataset' ...@@ -104,6 +104,31 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -111,35 +136,17 @@ data = dict( ...@@ -111,35 +136,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=(1333, 800), pipeline=train_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 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)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu.py
View file @ 49243848
...@@ -57,6 +57,35 @@ dataset_type = 'CocoDataset' ...@@ -57,6 +57,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False) 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( data = dict(
imgs_per_gpu=4, imgs_per_gpu=4,
workers_per_gpu=4, workers_per_gpu=4,
...@@ -64,37 +93,17 @@ data = dict( ...@@ -64,37 +93,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=[(1333, 640), (1333, 800)], pipeline=train_pipeline),
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),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict( optimizer = dict(
type='SGD', type='SGD',
...@@ -121,7 +130,6 @@ log_config = dict( ...@@ -121,7 +130,6 @@ log_config = dict(
# yapf:enable # yapf:enable
# runtime settings # runtime settings
total_epochs = 24 total_epochs = 24
device_ids = range(4)
dist_params = dict(backend='nccl') dist_params = dict(backend='nccl')
log_level = 'INFO' log_level = 'INFO'
work_dir = './work_dirs/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu' work_dir = './work_dirs/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu'
......
configs/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x.py
View file @ 49243848
...@@ -58,6 +58,35 @@ dataset_type = 'CocoDataset' ...@@ -58,6 +58,35 @@ dataset_type = 'CocoDataset'
data_root = 'data/coco/' data_root = 'data/coco/'
img_norm_cfg = dict( 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, 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( data = dict(
imgs_per_gpu=2, imgs_per_gpu=2,
workers_per_gpu=2, workers_per_gpu=2,
...@@ -65,37 +94,17 @@ data = dict( ...@@ -65,37 +94,17 @@ data = dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json', ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/', img_prefix=data_root + 'train2017/',
img_scale=[(1333, 640), (1333, 800)], pipeline=train_pipeline),
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),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json', ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/', img_prefix=data_root + 'val2017/',
img_scale=(1333, 800), pipeline=test_pipeline))
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=False,
test_mode=True))
# optimizer # optimizer
optimizer = dict( optimizer = dict(
type='SGD', type='SGD',
...@@ -122,7 +131,6 @@ log_config = dict( ...@@ -122,7 +131,6 @@ log_config = dict(
# yapf:enable # yapf:enable
# runtime settings # runtime settings
total_epochs = 24 total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl') dist_params = dict(backend='nccl')
log_level = 'INFO' log_level = 'INFO'
work_dir = './work_dirs/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x' work_dir = './work_dirs/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x'
......