Skip to content

邓媛媛 / pocdetection

Go to a project
Toggle navigation
Toggle navigation pinning
8cec0024 by yy_think
Options

init

0 parents
Expand all
Inline Side-by-side
Showing 1000 changed files with 4718 additions and 0 deletions

Too many changes to show.
Plain diff Email patch

To preserve performance only 1000 of 1000+ files are displayed.

.gitignore 0 → 100644
### Example user template template
### Example user template
# IntelliJ project files
.idea
*.iml
out
gen
map
config/config.py 0 → 100644
# detect config file
config = dict(
data=dict(
image_files='test.txt', # 需要检测的图像 .txt/dir/.jpg/.png
),
model=dict(
cuda='cpu',
class_txt='config/id/id_classes.txt',
config_files=['config/id/cascade_rcnn_r101_fpn_1x_coco_multiscale.py', 'config/id/faster_rcnn_r101_fpn_2x_coco_multiscale.py'],
checkpoint_files=['model/id/cascade_rcnn_r101_fpn_1x_multiscale_epoch_20.pth', 'model/id/faster_rcnn_r101_fpn_2x_multiscale_epoch_24.pth'],
),
fusion=dict(
type=['weighted_boxes_fusion'],
class_list=[[1, 5], [0, 2, 3, 4]],
weight_list=[1, 1], # 不同模型所占权重
iou=0.5, # 融合iou设置
score=0.4,
skip_box_thr=0.0001 # 排除低于此阈值score的box
),
show=False,
save_txt=True,
save_image=True,
out_dir='../out/test_20220516'
)
def load_config():
return config
config/head/faster_rcnn_r101_fpn_2x_coco.py 0 → 100644
model = dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=2,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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='L1Loss', loss_weight=1.0))),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
dataset_type = 'CocoDataset'
data_root = '/home/dyy/annotations/id'
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='CocoDataset',
ann_file=
'/home/dyy/annotations/head/coco/annotations/instances_train2017.json',
img_prefix='/home/dyy/annotations/head/coco/train2017/',
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]),
val=dict(
type='CocoDataset',
ann_file=
'/home/dyy/annotations/head/coco/annotations/instances_val2017.json',
img_prefix='/home/dyy/annotations/head/coco/val2017/',
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file=
'/home/dyy/annotations/head/coco/annotations/instances_val2017.json',
img_prefix='/home/dyy/annotations/head/coco/val2017/',
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=24)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
work_dir = '/home/dyy/project/mmdetection/work_dirs/head/faster_rcnn_r101_fpn_2x_coco.py'
auto_resume = False
gpu_ids = [0]
config/head/head_classes.txt 0 → 100644
head
hand
\ No newline at end of file
config/id/faster_rcnn_r101_fpn_2x_coco.py 0 → 100644
model = dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=6,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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='L1Loss', loss_weight=1.0))),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
dataset_type = 'CocoDataset'
data_root = '/home/situ/Disk6T/dyy/work/mmdetection/data/yuanjian'
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='CocoDataset',
ann_file='/home/situ/Disk6T/dyy/work/mmdetection/data/yuanjian/annotations/instances_train2017.json',
img_prefix='/home/situ/Disk6T/dyy/work/mmdetection/data/yuanjian/images/',
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]),
val=dict(
type='CocoDataset',
ann_file='/home/situ/Disk6T/dyy/work/mmdetection/data/yuanjian/annotations/instances_val2017.json',
img_prefix='/home/situ/Disk6T/dyy/work/mmdetection/data/yuanjian/images/',
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file='/home/situ/Disk6T/dyy/work/mmdetection/data/yuanjian/annotations/instances_val2017.json',
img_prefix='/home/situ/Disk6T/dyy/work/mmdetection/data/yuanjian/images/',
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=24)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
config/id/faster_rcnn_r101_fpn_2x_coco_multiscale.py 0 → 100644
model = dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=6,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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='L1Loss', loss_weight=1.0))),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
dataset_type = 'CocoDataset'
data_root = '/home/dyy/annotations/id/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=[(416, 416), (512, 512), (618, 618), (1333, 800)],
keep_ratio=True,
multiscale_mode='value'),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
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',
img_scale=[(416, 416), (512, 512), (618, 618), (1333, 800)],
keep_ratio=True,
multiscale_mode='value'),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='CocoDataset',
ann_file=
'/home/dyy/annotations/id/coco/annotations/instances_train2017.json',
img_prefix='/home/dyy/annotations/id/coco/train2017',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=[(416, 416), (512, 512), (618, 618), (1333, 800)],
keep_ratio=True,
multiscale_mode='value'),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]),
val=dict(
type='CocoDataset',
ann_file=
'/home/dyy/annotations/id/coco/annotations/instances_val2017.json',
img_prefix='/home/dyy/annotations/id/coco/val2017',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(
type='Resize',
img_scale=[(416, 416), (512, 512), (618, 618),
(1333, 800)],
keep_ratio=True,
multiscale_mode='value'),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file=
'/home/dyy/annotations/id/coco/annotations/instances_val2017.json',
img_prefix='/home/dyy/annotations/id/coco/val2017',
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=24)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
fp16 = dict(loss_scale=512.0)
work_dir = '/home/dyy/project/mmdetection/work_dirs/id/faster_rcnn_r101_fpn_2x_coco_multiscale'
auto_resume = False
gpu_ids = [0]
config/id/id_classes.txt 0 → 100644
id_front
id_back
zhiye_front
zhiye_back
file
phone
\ No newline at end of file
config/id/id_yolo5.yaml 0 → 100644
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
# Example usage: python train.py --data coco128.yaml
# parent
# ├── yolov5
# └── datasets
# └── coco128 ← downloads here
# Download script/URL (optional)
# download: bash data/scripts/get_coco.sh
# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
path: /home/situ/Disk6T/dyy/work/Yolov5/yolov5/datasets/YuanJian2022
train: /home/situ/Disk6T/dyy/work/Yolov5/yolov5/input/yuanjian_0112/train_0112.txt # 118287 images
val: /home/situ/Disk6T/dyy/work/Yolov5/yolov5/input/yuanjian_0112/valid_0112.txt # 5000 images
# Classes
nc: 6 # number of classes
names: ['id_front', 'id_back', 'zhiye_front', 'zhiye_back', 'file', 'phone'] # class names
config/id/retinanet_R_101_FPN_3x.yaml 0 → 100644
MODEL:
META_ARCHITECTURE: "RetinaNet"
BACKBONE:
NAME: "build_retinanet_resnet_fpn_backbone"
RESNETS:
DEPTH: 101
OUT_FEATURES: ["res3", "res4", "res5"]
ANCHOR_GENERATOR:
SIZES: !!python/object/apply:eval ["[[x, x * 2**(1.0/3), x * 2**(2.0/3) ] for x in [32, 64, 128, 256, 512 ]]"]
FPN:
IN_FEATURES: ["res3", "res4", "res5"]
RETINANET:
IOU_THRESHOLDS: [0.4, 0.5]
IOU_LABELS: [0, -1, 1]
SMOOTH_L1_LOSS_BETA: 0.0
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
DATASETS:
TRAIN: ("id_2017_train",)
TEST: ("id_2017_train",)
SOLVER:
IMS_PER_BATCH: 4
BASE_LR: 0.001 # Note that RetinaNet uses a different default learning rate
STEPS: (210000, 250000)
MAX_ITER: 270000
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2
data/mmdet_classes.txt 0 → 100644
id_front
id_back
zhiye_front
zhiye_back
file
phone
\ No newline at end of file
detect.py 0 → 100644
import glob
import shutil
import os
from config.config import load_config
import mmcv
from ensemble_boxes import *
import cv2
# 初始化文件夹
def init_dir(file_dir):
if not os.path.exists(file_dir):
os.mkdir(file_dir)
# 标准化输入文件格式
def init_input(cfg):
image_files = cfg['image_files']
if os.path.isdir(image_files):
image_files = [os.path.join(image_files, image_file) for image_file in os.listdir(image_files)]
elif os.path.exists(image_files):
if os.path.splitext(image_files)[-1] in ['.jpg', '.png']:
image_files = [image_files]
elif os.path.splitext(image_files)[-1] in ['.txt']:
image_files = [os.path.abspath(line.strip('\n').split(' ')[0]).replace('\\', '/') for line in open(image_files).readlines()]
elif isinstance(image_files, list) and os.path.splitext(image_files[0])[-1] in ['jpg', 'png']:
pass
elif '*.jpg' in image_files or '*.png' in image_files:
image_files = glob.glob(image_files)
else:
print('error input: ', image_files)
return
print(image_files)
return image_files
# 对mmdet输出结果处理
def mmdet_out(out, iou=0.5):
out_list = []
for i, label_list in enumerate(out):
for label in label_list:
if float(label[4]) < iou:
continue
out_list.append([i, label[4], label[0], label[1], label[2], label[3]])
return out_list
# box归一化
def box_normalize(box, size):
box[0] = box[0] / size[0]
box[1] = box[1] / size[1]
box[2] = box[2] / size[0]
box[3] = box[3] / size[1]
for i, s in enumerate(box):
if s > 1:
box[i] = 1
elif s < 0:
box[i] = 0
return box
# box反归一化
def box_re_std(box, size):
box[0] = box[0] * size[0]
box[1] = box[1] * size[1]
box[2] = box[2] * size[0]
box[3] = box[3] * size[1]
return box.tolist()
# box融合
def boxes_fusion(cfg, boxes_list):
rs = []
if 'class_fusion' in cfg['type']:
assert len(cfg['class_list']) == len(boxes_list)
for i in range(len(boxes_list)):
for box in boxes_list[i]:
if box[0] in cfg['class_list']:
rs.append(box)
if 'weighted_boxes_fusion' in cfg['type']:
if rs:
boxes_list.append(rs)
cfg['weight_list'].append(1)
scores_list = [[box[1] for box in boxes] for boxes in boxes_list]
labels_list = [[int(box[0]) for box in boxes] for boxes in boxes_list]
boxes_list = [[box_normalize(box[2:], cfg['size']) for box in boxes] for boxes in boxes_list]
boxes, scores, labels = weighted_boxes_fusion(boxes_list, scores_list, labels_list, weights=cfg['weight_list'],
iou_thr=cfg['iou'], skip_box_thr=cfg['skip_box_thr'])
for i, box in enumerate(boxes):
if scores[i] > cfg['score']:
rs.append([labels[i], scores[i]] + box_re_std(box, cfg['size']))
return rs
# mm_detect
def mmdetect(models, fusion, img):
if os.path.exists(models['class_txt']):
shutil.copy(models['class_txt'], 'data/mmdet_classes.txt')
from mmdet.apis import init_detector, inference_detector
boxes_list = []
if isinstance(img, str):
img = mmcv.imread(img)
fusion['size'] = img.shape[:-1][::-1]
for i, config in enumerate(models['config_files']):
model = init_detector(config, os.path.abspath( models['checkpoint_files'][i]), device=models['cuda'])
out = inference_detector(model, img)
out = mmdet_out(out)
boxes_list.append(out)
if fusion:
boxes_list = boxes_fusion(fusion, boxes_list)
print(boxes_list)
return boxes_list
def run():
cfg = load_config() # 加载config文件
# 初始化
init_dir(cfg['out_dir'])
if cfg['save_image']:
image_dir = os.path.join(cfg['out_dir'], 'image')
init_dir(image_dir)
if cfg['save_txt']:
txt_dir = os.path.join(cfg['out_dir'], 'label')
init_dir(txt_dir)
image_files = init_input(cfg['data'])
# detect
for image_file in image_files:
image = cv2.imread(image_file)
boxes = mmdetect(cfg['model'], cfg['fusion'], image_file)
if cfg['save_txt']:
out_txt = os.path.join(txt_dir, image_file.split('/')[-1].replace('.jpg', '.txt'))
f = open(out_txt, 'w')
for box in boxes:
f.write(' {} {} {} {} {} {}'.format(box[0], box[1], box[2], box[3], box[4], box[5]))
f.write('\n')
for box in boxes:
cv2.rectangle(image, (int(box[2]), int(box[3])), (int(box[4]), int(box[5])), (255, 0, 255))
cv2.putText(image, '{} {:.2f}'.format(int(box[0]), box[1]), (int(box[2]), int(box[3]) + 5), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 255), thickness=2)
if cfg['show']:
cv2.imshow('image', image)
if cfg['save_image']:
image_path = os.path.join(image_dir, image_file.split('/')[-1])
cv2.imwrite(image_path, image)
if __name__ == '__main__':
run()
mmdet/.mim/configs/_base_/datasets/cityscapes_detection.py 0 → 100644
# 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(
samples_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 + 'leftImg8bit/train/',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'leftImg8bit/val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_test.json',
img_prefix=data_root + 'leftImg8bit/test/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
mmdet/.mim/configs/_base_/datasets/cityscapes_instance.py 0 → 100644
# 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(
samples_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 + 'leftImg8bit/train/',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'leftImg8bit/val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_test.json',
img_prefix=data_root + 'leftImg8bit/test/',
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
mmdet/.mim/configs/_base_/datasets/coco_detection.py 0 → 100644
# 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(
samples_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))
evaluation = dict(interval=1, metric='bbox')
mmdet/.mim/configs/_base_/datasets/coco_instance.py 0 → 100644
# 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(
samples_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))
evaluation = dict(metric=['bbox', 'segm'])
mmdet/.mim/configs/_base_/datasets/coco_instance_semantic.py 0 → 100644
# 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, with_seg=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_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/',
seg_prefix=data_root + 'stuffthingmaps/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))
evaluation = dict(metric=['bbox', 'segm'])
mmdet/.mim/configs/_base_/datasets/coco_panoptic.py 0 → 100644
# dataset settings
dataset_type = 'CocoPanopticDataset'
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='LoadPanopticAnnotations',
with_bbox=True,
with_mask=True,
with_seg=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegRescale', scale_factor=1 / 4),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/panoptic_train2017.json',
img_prefix=data_root + 'train2017/',
seg_prefix=data_root + 'annotations/panoptic_train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/panoptic_val2017.json',
img_prefix=data_root + 'val2017/',
seg_prefix=data_root + 'annotations/panoptic_val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/panoptic_val2017.json',
img_prefix=data_root + 'val2017/',
seg_prefix=data_root + 'annotations/panoptic_val2017/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric=['PQ'])
mmdet/.mim/configs/_base_/datasets/deepfashion.py 0 → 100644
# dataset settings
dataset_type = 'DeepFashionDataset'
data_root = 'data/DeepFashion/In-shop/'
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=(750, 1101), 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=(750, 1101),
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=1,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
img_prefix=data_root + 'Img/',
pipeline=train_pipeline,
data_root=data_root),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
img_prefix=data_root + 'Img/',
pipeline=test_pipeline,
data_root=data_root),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/DeepFashion_segmentation_gallery.json',
img_prefix=data_root + 'Img/',
pipeline=test_pipeline,
data_root=data_root))
evaluation = dict(interval=5, metric=['bbox', 'segm'])
mmdet/.mim/configs/_base_/datasets/lvis_v0.5_instance.py 0 → 100644
# dataset settings
_base_ = 'coco_instance.py'
dataset_type = 'LVISV05Dataset'
data_root = 'data/lvis_v0.5/'
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
_delete_=True,
type='ClassBalancedDataset',
oversample_thr=1e-3,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v0.5_train.json',
img_prefix=data_root + 'train2017/')),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v0.5_val.json',
img_prefix=data_root + 'val2017/'),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v0.5_val.json',
img_prefix=data_root + 'val2017/'))
evaluation = dict(metric=['bbox', 'segm'])
mmdet/.mim/configs/_base_/datasets/lvis_v1_instance.py 0 → 100644
# dataset settings
_base_ = 'coco_instance.py'
dataset_type = 'LVISV1Dataset'
data_root = 'data/lvis_v1/'
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
_delete_=True,
type='ClassBalancedDataset',
oversample_thr=1e-3,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v1_train.json',
img_prefix=data_root)),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v1_val.json',
img_prefix=data_root),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v1_val.json',
img_prefix=data_root))
evaluation = dict(metric=['bbox', 'segm'])
mmdet/.mim/configs/_base_/datasets/openimages_detection.py 0 → 100644
# dataset settings
dataset_type = 'OpenImagesDataset'
data_root = 'data/OpenImages/'
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, denorm_bbox=True),
dict(type='Resize', img_scale=(1024, 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=(1024, 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(
samples_per_gpu=2,
workers_per_gpu=0, # workers_per_gpu > 0 may occur out of memory
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/oidv6-train-annotations-bbox.csv',
img_prefix=data_root + 'OpenImages/train/',
label_file=data_root + 'annotations/class-descriptions-boxable.csv',
hierarchy_file=data_root +
'annotations/bbox_labels_600_hierarchy.json',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/validation-annotations-bbox.csv',
img_prefix=data_root + 'OpenImages/validation/',
label_file=data_root + 'annotations/class-descriptions-boxable.csv',
hierarchy_file=data_root +
'annotations/bbox_labels_600_hierarchy.json',
meta_file=data_root + 'annotations/validation-image-metas.pkl',
image_level_ann_file=data_root +
'annotations/validation-annotations-human-imagelabels-boxable.csv',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/validation-annotations-bbox.csv',
img_prefix=data_root + 'OpenImages/validation/',
label_file=data_root + 'annotations/class-descriptions-boxable.csv',
hierarchy_file=data_root +
'annotations/bbox_labels_600_hierarchy.json',
meta_file=data_root + 'annotations/validation-image-metas.pkl',
image_level_ann_file=data_root +
'annotations/validation-annotations-human-imagelabels-boxable.csv',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='mAP')
mmdet/.mim/configs/_base_/datasets/voc0712.py 0 → 100644
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1000, 600),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=3,
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'VOC2007/ImageSets/Main/trainval.txt',
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='mAP')
mmdet/.mim/configs/_base_/datasets/wider_face.py 0 → 100644
# dataset settings
dataset_type = 'WIDERFaceDataset'
data_root = 'data/WIDERFace/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', to_float32=True),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(
type='Expand',
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
dict(
type='MinIoURandomCrop',
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
min_crop_size=0.3),
dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(300, 300),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=False),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=60,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'train.txt',
img_prefix=data_root + 'WIDER_train/',
min_size=17,
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'val.txt',
img_prefix=data_root + 'WIDER_val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'val.txt',
img_prefix=data_root + 'WIDER_val/',
pipeline=test_pipeline))
mmdet/.mim/configs/_base_/default_runtime.py 0 → 100644
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
# disable opencv multithreading to avoid system being overloaded
opencv_num_threads = 0
# set multi-process start method as `fork` to speed up the training
mp_start_method = 'fork'
mmdet/.mim/configs/_base_/models/cascade_mask_rcnn_r50_fpn.py 0 → 100644
# model settings
model = dict(
type='CascadeRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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)),
roi_head=dict(
type='CascadeRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
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)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
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)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
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))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
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=80,
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,
match_low_quality=True,
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_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
match_low_quality=False,
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),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
match_low_quality=False,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
mmdet/.mim/configs/_base_/models/cascade_rcnn_r50_fpn.py 0 → 100644
# model settings
model = dict(
type='CascadeRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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)),
roi_head=dict(
type='CascadeRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
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)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
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)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
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))
]),
# 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,
match_low_quality=True,
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_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
match_low_quality=False,
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),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
match_low_quality=False,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
mmdet/.mim/configs/_base_/models/fast_rcnn_r50_fpn.py 0 → 100644
# model settings
model = dict(
type='FastRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
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(
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
mmdet/.mim/configs/_base_/models/faster_rcnn_r50_caffe_c4.py 0 → 100644
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=3,
strides=(1, 2, 2),
dilations=(1, 1, 1),
out_indices=(2, ),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
rpn_head=dict(
type='RPNHead',
in_channels=1024,
feat_channels=1024,
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4, 8, 16, 32],
ratios=[0.5, 1.0, 2.0],
strides=[16]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
shared_head=dict(
type='ResLayer',
depth=50,
stage=3,
stride=2,
dilation=1,
style='caffe',
norm_cfg=norm_cfg,
norm_eval=True),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=1024,
featmap_strides=[16]),
bbox_head=dict(
type='BBoxHead',
with_avg_pool=True,
roi_feat_size=7,
in_channels=2048,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', 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,
match_low_quality=True,
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_pre=12000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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_pre=6000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
mmdet/.mim/configs/_base_/models/faster_rcnn_r50_caffe_dc5.py 0 → 100644
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
strides=(1, 2, 2, 1),
dilations=(1, 1, 1, 2),
out_indices=(3, ),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
rpn_head=dict(
type='RPNHead',
in_channels=2048,
feat_channels=2048,
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4, 8, 16, 32],
ratios=[0.5, 1.0, 2.0],
strides=[16]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=2048,
featmap_strides=[16]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=2048,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', 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,
match_low_quality=True,
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_pre=12000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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=dict(type='nms', iou_threshold=0.7),
nms_pre=6000,
max_per_img=1000,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
mmdet/.mim/configs/_base_/models/faster_rcnn_r50_fpn.py 0 → 100644
# model settings
model = dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', 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,
match_low_quality=True,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)
# soft-nms is also supported for rcnn testing
# e.g., nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.05)
))
mmdet/.mim/configs/_base_/models/mask_rcnn_r50_caffe_c4.py 0 → 100644
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='MaskRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=3,
strides=(1, 2, 2),
dilations=(1, 1, 1),
out_indices=(2, ),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
rpn_head=dict(
type='RPNHead',
in_channels=1024,
feat_channels=1024,
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4, 8, 16, 32],
ratios=[0.5, 1.0, 2.0],
strides=[16]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
shared_head=dict(
type='ResLayer',
depth=50,
stage=3,
stride=2,
dilation=1,
style='caffe',
norm_cfg=norm_cfg,
norm_eval=True),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=1024,
featmap_strides=[16]),
bbox_head=dict(
type='BBoxHead',
with_avg_pool=True,
roi_feat_size=7,
in_channels=2048,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
mask_roi_extractor=None,
mask_head=dict(
type='FCNMaskHead',
num_convs=0,
in_channels=2048,
conv_out_channels=256,
num_classes=80,
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,
match_low_quality=True,
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_pre=12000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=False,
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=14,
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=6000,
nms=dict(type='nms', iou_threshold=0.7),
max_per_img=1000,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
mmdet/.mim/configs/_base_/models/mask_rcnn_r50_fpn.py 0 → 100644
# model settings
model = dict(
type='MaskRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
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=80,
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,
match_low_quality=True,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=True,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
mmdet/.mim/configs/_base_/models/retinanet_r50_fpn.py 0 → 100644
# model settings
model = dict(
type='RetinaNet',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_input',
num_outs=5),
bbox_head=dict(
type='RetinaHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
octave_base_scale=4,
scales_per_octave=3,
ratios=[0.5, 1.0, 2.0],
strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
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_threshold=0.5),
max_per_img=100))
mmdet/.mim/configs/_base_/models/rpn_r50_caffe_c4.py 0 → 100644
# model settings
model = dict(
type='RPN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=3,
strides=(1, 2, 2),
dilations=(1, 1, 1),
out_indices=(2, ),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
neck=None,
rpn_head=dict(
type='RPNHead',
in_channels=1024,
feat_channels=1024,
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4, 8, 16, 32],
ratios=[0.5, 1.0, 2.0],
strides=[16]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', 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)),
test_cfg=dict(
rpn=dict(
nms_pre=12000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0)))
mmdet/.mim/configs/_base_/models/rpn_r50_fpn.py 0 → 100644
# model settings
model = dict(
type='RPN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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='L1Loss', 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)),
test_cfg=dict(
rpn=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0)))
mmdet/.mim/configs/_base_/models/ssd300.py 0 → 100644
# model settings
input_size = 300
model = dict(
type='SingleStageDetector',
backbone=dict(
type='SSDVGG',
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://vgg16_caffe')),
neck=dict(
type='SSDNeck',
in_channels=(512, 1024),
out_channels=(512, 1024, 512, 256, 256, 256),
level_strides=(2, 2, 1, 1),
level_paddings=(1, 1, 0, 0),
l2_norm_scale=20),
bbox_head=dict(
type='SSDHead',
in_channels=(512, 1024, 512, 256, 256, 256),
num_classes=80,
anchor_generator=dict(
type='SSDAnchorGenerator',
scale_major=False,
input_size=input_size,
basesize_ratio_range=(0.15, 0.9),
strides=[8, 16, 32, 64, 100, 300],
ratios=[[2], [2, 3], [2, 3], [2, 3], [2], [2]]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[0.1, 0.1, 0.2, 0.2])),
# model training and testing settings
train_cfg=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False),
test_cfg=dict(
nms_pre=1000,
nms=dict(type='nms', iou_threshold=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200))
cudnn_benchmark = True
mmdet/.mim/configs/_base_/schedules/schedule_1x.py 0 → 100644
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
mmdet/.mim/configs/_base_/schedules/schedule_20e.py 0 → 100644
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[16, 19])
runner = dict(type='EpochBasedRunner', max_epochs=20)
mmdet/.mim/configs/_base_/schedules/schedule_2x.py 0 → 100644
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=24)
mmdet/.mim/configs/albu_example/README.md 0 → 100644
# Albu Example
> [Albumentations: fast and flexible image augmentations](https://arxiv.org/abs/1809.06839)
<!-- [OTHERS] -->
## Abstract
Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve output labels. In computer vision domain, image augmentations have become a common implicit regularization technique to combat overfitting in deep convolutional neural networks and are ubiquitously used to improve performance. While most deep learning frameworks implement basic image transformations, the list is typically limited to some variations and combinations of flipping, rotating, scaling, and cropping. Moreover, the image processing speed varies in existing tools for image augmentation. We present Albumentations, a fast and flexible library for image augmentations with many various image transform operations available, that is also an easy-to-use wrapper around other augmentation libraries. We provide examples of image augmentations for different computer vision tasks and show that Albumentations is faster than other commonly used image augmentation tools on the most of commonly used image transformations.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143870703-74f3ea3f-ae23-4035-9856-746bc3f88464.png" height="400" />
</div>
## Results and Models
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
|:---------:|:-------:|:-------:|:--------:|:--------------:|:------:|:-------:|:------:|:--------:|
| R-50 | pytorch | 1x | 4.4 | 16.6 | 38.0 | 34.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/albu_example/mask_rcnn_r50_fpn_albu_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208-ab203bcd.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208_225520.log.json) |
## Citation
```latex
@article{2018arXiv180906839B,
author = {A. Buslaev, A. Parinov, E. Khvedchenya, V.~I. Iglovikov and A.~A. Kalinin},
title = "{Albumentations: fast and flexible image augmentations}",
journal = {ArXiv e-prints},
eprint = {1809.06839},
year = 2018
}
```
mmdet/.mim/configs/albu_example/mask_rcnn_r50_fpn_albu_1x_coco.py 0 → 100644
_base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py'
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'))
]
data = dict(train=dict(pipeline=train_pipeline))
mmdet/.mim/configs/atss/README.md 0 → 100644
# ATSS
> [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://arxiv.org/abs/1912.02424)
<!-- [ALGORITHM] -->
## Abstract
Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to 50.7% AP without introducing any overhead.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143870776-c81168f5-e8b2-44ee-978b-509e4372c5c9.png"/>
</div>
## Results and Models
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
|:---------:|:-------:|:-------:|:--------:|:--------------:|:------:|:------:|:--------:|
| R-50 | pytorch | 1x | 3.7 | 19.7 | 39.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/atss/atss_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209-985f7bd0.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209_102539.log.json) |
| R-101 | pytorch | 1x | 5.6 | 12.3 | 41.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/atss/atss_r101_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.log.json) |
## Citation
```latex
@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}
}
```
mmdet/.mim/configs/atss/atss_r101_fpn_1x_coco.py 0 → 100644
_base_ = './atss_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')))
mmdet/.mim/configs/atss/atss_r50_fpn_1x_coco.py 0 → 100644
_base_ = [
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
type='ATSS',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_output',
num_outs=5),
bbox_head=dict(
type='ATSSHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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_threshold=0.6),
max_per_img=100))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
mmdet/.mim/configs/atss/metafile.yml 0 → 100644
Collections:
- Name: ATSS
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x V100 GPUs
Architecture:
- ATSS
- FPN
- ResNet
Paper:
URL: https://arxiv.org/abs/1912.02424
Title: 'Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection'
README: configs/atss/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.0.0/mmdet/models/detectors/atss.py#L6
Version: v2.0.0
Models:
- Name: atss_r50_fpn_1x_coco
In Collection: ATSS
Config: configs/atss/atss_r50_fpn_1x_coco.py
Metadata:
Training Memory (GB): 3.7
inference time (ms/im):
- value: 50.76
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (800, 1333)
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 39.4
Weights: https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209-985f7bd0.pth
- Name: atss_r101_fpn_1x_coco
In Collection: ATSS
Config: configs/atss/atss_r101_fpn_1x_coco.py
Metadata:
Training Memory (GB): 5.6
inference time (ms/im):
- value: 81.3
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (800, 1333)
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 41.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.pth
mmdet/.mim/configs/autoassign/README.md 0 → 100644
# AutoAssign
> [AutoAssign: Differentiable Label Assignment for Dense Object Detection](https://arxiv.org/abs/2007.03496)
<!-- [ALGORITHM] -->
## Abstract
Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully differentiable weighting mechanism. During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions. To adapt to object appearances, Confidence Weighting is proposed to adjust the specific assign strategy of each instance. The two weighting modules are then combined to generate positive and negative weights to adjust each location's confidence. Extensive experiments on the MS COCO show that our method steadily surpasses other best sampling strategies by large margins with various backbones. Moreover, our best model achieves 52.1% AP, outperforming all existing one-stage detectors. Besides, experiments on other datasets, e.g., PASCAL VOC, Objects365, and WiderFace, demonstrate the broad applicability of AutoAssign.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143870875-33567e44-0584-4470-9a90-0df0fb6c1fe2.png"/>
</div>
## Results and Models
| Backbone | Style | Lr schd | Mem (GB) | box AP | Config | Download |
|:---------:|:-------:|:-------:|:--------:|:------:|:------:|:--------:|
| R-50 | caffe | 1x | 4.08 | 40.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/autoassign/autoassign_r50_fpn_8x2_1x_coco.py) |[model](https://download.openmmlab.com/mmdetection/v2.0/autoassign/auto_assign_r50_fpn_1x_coco/auto_assign_r50_fpn_1x_coco_20210413_115540-5e17991f.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/autoassign/auto_assign_r50_fpn_1x_coco/auto_assign_r50_fpn_1x_coco_20210413_115540-5e17991f.log.json) |
**Note**:
1. We find that the performance is unstable with 1x setting and may fluctuate by about 0.3 mAP. mAP 40.3 ~ 40.6 is acceptable. Such fluctuation can also be found in the original implementation.
2. You can get a more stable results ~ mAP 40.6 with a schedule total 13 epoch, and learning rate is divided by 10 at 10th and 13th epoch.
## Citation
```latex
@article{zhu2020autoassign,
title={AutoAssign: Differentiable Label Assignment for Dense Object Detection},
author={Zhu, Benjin and Wang, Jianfeng and Jiang, Zhengkai and Zong, Fuhang and Liu, Songtao and Li, Zeming and Sun, Jian},
journal={arXiv preprint arXiv:2007.03496},
year={2020}
}
```
mmdet/.mim/configs/autoassign/autoassign_r50_fpn_8x2_1x_coco.py 0 → 100644
# We follow the original implementation which
# adopts the Caffe pre-trained backbone.
_base_ = [
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
type='AutoAssign',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
relu_before_extra_convs=True,
init_cfg=dict(type='Caffe2Xavier', layer='Conv2d')),
bbox_head=dict(
type='AutoAssignHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
strides=[8, 16, 32, 64, 128],
loss_bbox=dict(type='GIoULoss', loss_weight=5.0)),
train_cfg=None,
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))
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(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(lr=0.01, paramwise_cfg=dict(norm_decay_mult=0.))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[8, 11])
total_epochs = 12
mmdet/.mim/configs/autoassign/metafile.yml 0 → 100644
Collections:
- Name: AutoAssign
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x V100 GPUs
Architecture:
- AutoAssign
- FPN
- ResNet
Paper:
URL: https://arxiv.org/abs/2007.03496
Title: 'AutoAssign: Differentiable Label Assignment for Dense Object Detection'
README: configs/autoassign/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.12.0/mmdet/models/detectors/autoassign.py#L6
Version: v2.12.0
Models:
- Name: autoassign_r50_fpn_8x2_1x_coco
In Collection: AutoAssign
Config: configs/autoassign/autoassign_r50_fpn_8x2_1x_coco.py
Metadata:
Training Memory (GB): 4.08
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.4
Weights: https://download.openmmlab.com/mmdetection/v2.0/autoassign/auto_assign_r50_fpn_1x_coco/auto_assign_r50_fpn_1x_coco_20210413_115540-5e17991f.pth
mmdet/.mim/configs/carafe/README.md 0 → 100644
# CARAFE
> [CARAFE: Content-Aware ReAssembly of FEatures](https://arxiv.org/abs/1905.02188)
<!-- [ALGORITHM] -->
## Abstract
Feature upsampling is a key operation in a number of modern convolutional network architectures, e.g. feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose Content-Aware ReAssembly of FEatures (CARAFE), a universal, lightweight and highly effective operator to fulfill this goal. CARAFE has several appealing properties: (1) Large field of view. Unlike previous works (e.g. bilinear interpolation) that only exploit sub-pixel neighborhood, CARAFE can aggregate contextual information within a large receptive field. (2) Content-aware handling. Instead of using a fixed kernel for all samples (e.g. deconvolution), CARAFE enables instance-specific content-aware handling, which generates adaptive kernels on-the-fly. (3) Lightweight and fast to compute. CARAFE introduces little computational overhead and can be readily integrated into modern network architectures. We conduct comprehensive evaluations on standard benchmarks in object detection, instance/semantic segmentation and inpainting. CARAFE shows consistent and substantial gains across all the tasks (1.2%, 1.3%, 1.8%, 1.1db respectively) with negligible computational overhead. It has great potential to serve as a strong building block for future research. It has great potential to serve as a strong building block for future research.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143872016-48225685-0e59-49cf-bd65-a50ee04ca8a2.png"/>
</div>
## Results and Models
The results on COCO 2017 val is shown in the below table.
| Method | Backbone | Style | Lr schd | Test Proposal Num | Inf time (fps) | Box AP | Mask AP | Config | Download |
|:--------------------:|:--------:|:-------:|:-------:|:-----------------:|:--------------:|:------:|:-------:|:------:|:--------:|
| Faster R-CNN w/ CARAFE | R-50-FPN | pytorch | 1x | 1000 | 16.5 | 38.6 | 38.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/carafe/faster_rcnn_r50_fpn_carafe_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/carafe/faster_rcnn_r50_fpn_carafe_1x_coco/faster_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.386_20200504_175733-385a75b7.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/carafe/faster_rcnn_r50_fpn_carafe_1x_coco/faster_rcnn_r50_fpn_carafe_1x_coco_20200504_175733.log.json) |
| - | - | - | - | 2000 | | | | |
| Mask R-CNN w/ CARAFE | R-50-FPN | pytorch | 1x | 1000 | 14.0 | 39.3 | 35.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/carafe/mask_rcnn_r50_fpn_carafe_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/carafe/mask_rcnn_r50_fpn_carafe_1x_coco/mask_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.393__segm_mAP-0.358_20200503_135957-8687f195.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/carafe/mask_rcnn_r50_fpn_carafe_1x_coco/mask_rcnn_r50_fpn_carafe_1x_coco_20200503_135957.log.json) |
| - | - | - | - | 2000 | | | | |
## Implementation
The CUDA implementation of CARAFE can be find at https://github.com/myownskyW7/CARAFE.
## Citation
We provide config files to reproduce the object detection & instance segmentation results in the ICCV 2019 Oral paper for [CARAFE: Content-Aware ReAssembly of FEatures](https://arxiv.org/abs/1905.02188).
```latex
@inproceedings{Wang_2019_ICCV,
title = {CARAFE: Content-Aware ReAssembly of FEatures},
author = {Wang, Jiaqi and Chen, Kai and Xu, Rui and Liu, Ziwei and Loy, Chen Change and Lin, Dahua},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}
```
mmdet/.mim/configs/carafe/faster_rcnn_r50_fpn_carafe_1x_coco.py 0 → 100644
_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(
neck=dict(
type='FPN_CARAFE',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
start_level=0,
end_level=-1,
norm_cfg=None,
act_cfg=None,
order=('conv', 'norm', 'act'),
upsample_cfg=dict(
type='carafe',
up_kernel=5,
up_group=1,
encoder_kernel=3,
encoder_dilation=1,
compressed_channels=64)))
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=64),
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=64),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
mmdet/.mim/configs/carafe/mask_rcnn_r50_fpn_carafe_1x_coco.py 0 → 100644
_base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py'
model = dict(
neck=dict(
type='FPN_CARAFE',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
start_level=0,
end_level=-1,
norm_cfg=None,
act_cfg=None,
order=('conv', 'norm', 'act'),
upsample_cfg=dict(
type='carafe',
up_kernel=5,
up_group=1,
encoder_kernel=3,
encoder_dilation=1,
compressed_channels=64)),
roi_head=dict(
mask_head=dict(
upsample_cfg=dict(
type='carafe',
scale_factor=2,
up_kernel=5,
up_group=1,
encoder_kernel=3,
encoder_dilation=1,
compressed_channels=64))))
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=64),
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=64),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
mmdet/.mim/configs/carafe/metafile.yml 0 → 100644
Collections:
- Name: CARAFE
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x V100 GPUs
Architecture:
- RPN
- FPN_CARAFE
- ResNet
- RoIPool
Paper:
URL: https://arxiv.org/abs/1905.02188
Title: 'CARAFE: Content-Aware ReAssembly of FEatures'
README: configs/carafe/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.12.0/mmdet/models/necks/fpn_carafe.py#L11
Version: v2.12.0
Models:
- Name: faster_rcnn_r50_fpn_carafe_1x_coco
In Collection: CARAFE
Config: configs/carafe/faster_rcnn_r50_fpn_carafe_1x_coco.py
Metadata:
Training Memory (GB): 4.26
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 38.6
- Task: Instance Segmentation
Dataset: COCO
Metrics:
mask AP: 38.6
Weights: https://download.openmmlab.com/mmdetection/v2.0/carafe/faster_rcnn_r50_fpn_carafe_1x_coco/faster_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.386_20200504_175733-385a75b7.pth
- Name: mask_rcnn_r50_fpn_carafe_1x_coco
In Collection: CARAFE
Config: configs/carafe/mask_rcnn_r50_fpn_carafe_1x_coco.py
Metadata:
Training Memory (GB): 4.31
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 39.3
- Task: Instance Segmentation
Dataset: COCO
Metrics:
mask AP: 35.6
Weights: https://download.openmmlab.com/mmdetection/v2.0/carafe/mask_rcnn_r50_fpn_carafe_1x_coco/mask_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.393__segm_mAP-0.358_20200503_135957-8687f195.pth
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet101_caffe')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_mstrain_3x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_caffe_fpn_mstrain_3x_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet101_caffe')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_20e_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_mstrain_3x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_mstrain_3x_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py 0 → 100644
_base_ = ['./cascade_mask_rcnn_r50_fpn_1x_coco.py']
model = dict(
backbone=dict(
norm_cfg=dict(requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')))
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], 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(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r50_caffe_fpn_mstrain_3x_coco.py 0 → 100644
_base_ = ['./cascade_mask_rcnn_r50_fpn_mstrain_3x_coco.py']
model = dict(
backbone=dict(
norm_cfg=dict(requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')))
# use caffe img_norm
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
# In mstrain 3x config, img_scale=[(1333, 640), (1333, 800)],
# multiscale_mode='range'
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(
type='Resize',
img_scale=[(1333, 640), (1333, 800)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='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(
train=dict(dataset=dict(pipeline=train_pipeline)),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py 0 → 100644
_base_ = [
'../_base_/models/cascade_mask_rcnn_r50_fpn.py',
'../_base_/datasets/coco_instance.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco.py 0 → 100644
_base_ = [
'../_base_/models/cascade_mask_rcnn_r50_fpn.py',
'../_base_/datasets/coco_instance.py',
'../_base_/schedules/schedule_20e.py', '../_base_/default_runtime.py'
]
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_mstrain_3x_coco.py 0 → 100644
_base_ = [
'../common/mstrain_3x_coco_instance.py',
'../_base_/models/cascade_mask_rcnn_r50_fpn.py'
]
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_32x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_32x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_mstrain_3x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_mstrain_3x_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_32x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_x101_32x8d_fpn_mstrain_3x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_mstrain_3x_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=8,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
style='pytorch',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnext101_32x8d')))
# ResNeXt-101-32x8d model trained with Caffe2 at FB,
# so the mean and std need to be changed.
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675],
std=[57.375, 57.120, 58.395],
to_rgb=False)
# In mstrain 3x config, img_scale=[(1333, 640), (1333, 800)],
# multiscale_mode='range'
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(
type='Resize',
img_scale=[(1333, 640), (1333, 800)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='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(
train=dict(dataset=dict(pipeline=train_pipeline)),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_mstrain_3x_coco.py 0 → 100644
_base_ = './cascade_mask_rcnn_r50_fpn_mstrain_3x_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_r101_caffe_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_caffe_fpn_1x_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet101_caffe')))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_r101_fpn_20e_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_20e_coco.py'
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_r50_caffe_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
norm_cfg=dict(requires_grad=False),
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')))
# use caffe img_norm
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], 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(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py 0 → 100644
_base_ = [
'../_base_/models/cascade_rcnn_r50_fpn.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_r50_fpn_20e_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_1x_coco.py'
# learning policy
lr_config = dict(step=[16, 19])
runner = dict(type='EpochBasedRunner', max_epochs=20)
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_32x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_20e_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_20e_coco.py'
model = dict(
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_32x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_1x_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_1x_coco.py'
model = dict(
type='CascadeRCNN',
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')))
mmdet/.mim/configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_20e_coco.py 0 → 100644
_base_ = './cascade_rcnn_r50_fpn_20e_coco.py'
model = dict(
type='CascadeRCNN',
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')))
mmdet/.mim/configs/cascade_rpn/README.md 0 → 100644
# Cascade RPN
> [Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution](https://arxiv.org/abs/1909.06720)
<!-- [ALGORITHM] -->
## Abstract
This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection performance by systematically addressing the limitation of the conventional RPN that heuristically defines the anchors and aligns the features to the anchors. First, instead of using multiple anchors with predefined scales and aspect ratios, Cascade RPN relies on a single anchor per location and performs multi-stage refinement. Each stage is progressively more stringent in defining positive samples by starting out with an anchor-free metric followed by anchor-based metrics in the ensuing stages. Second, to attain alignment between the features and the anchors throughout the stages, adaptive convolution is proposed that takes the anchors in addition to the image features as its input and learns the sampled features guided by the anchors. A simple implementation of a two-stage Cascade RPN achieves AR 13.4 points higher than that of the conventional RPN, surpassing any existing region proposal methods. When adopting to Fast R-CNN and Faster R-CNN, Cascade RPN can improve the detection mAP by 3.1 and 3.5 points, respectively.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143872368-1580193a-d19c-4723-a579-c7ed2d5da4d1.png"/>
</div>
## Results and Models
### Region proposal performance
| Method | Backbone | Style | Mem (GB) | Train time (s/iter) | Inf time (fps) | AR 1000 | Config | Download |
|:------:|:--------:|:-----:|:--------:|:-------------------:|:--------------:|:-------:|:-------:|:--------------------------------------:|
| CRPN | R-50-FPN | caffe | - | - | - | 72.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rpn/crpn_r50_caffe_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/cascade_rpn/crpn_r50_caffe_fpn_1x_coco/cascade_rpn_r50_caffe_fpn_1x_coco-7aa93cef.pth) |
### Detection performance
| Method | Proposal | Backbone | Style | Schedule | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Config | Download |
|:-------------:|:-----------:|:--------:|:-------:|:--------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------------------------------------------:|
| Fast R-CNN | Cascade RPN | R-50-FPN | caffe | 1x | - | - | - | 39.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rpn/crpn_fast_rcnn_r50_caffe_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/cascade_rpn/crpn_fast_rcnn_r50_caffe_fpn_1x_coco/crpn_fast_rcnn_r50_caffe_fpn_1x_coco-cb486e66.pth) |
| Faster R-CNN | Cascade RPN | R-50-FPN | caffe | 1x | - | - | - | 40.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rpn/crpn_faster_rcnn_r50_caffe_fpn_1x_coco.py) |[model](https://download.openmmlab.com/mmdetection/v2.0/cascade_rpn/crpn_faster_rcnn_r50_caffe_fpn_1x_coco/crpn_faster_rcnn_r50_caffe_fpn_1x_coco-c8283cca.pth) |
## Citation
We provide the code for reproducing experiment results of [Cascade RPN](https://arxiv.org/abs/1909.06720).
```latex
@inproceedings{vu2019cascade,
title={Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution},
author={Vu, Thang and Jang, Hyunjun and Pham, Trung X and Yoo, Chang D},
booktitle={Conference on Neural Information Processing Systems (NeurIPS)},
year={2019}
}
```
mmdet/.mim/configs/cascade_rpn/crpn_fast_rcnn_r50_caffe_fpn_1x_coco.py 0 → 100644
_base_ = '../fast_rcnn/fast_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
roi_head=dict(
bbox_head=dict(
bbox_coder=dict(target_stds=[0.04, 0.04, 0.08, 0.08]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.5),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rcnn=dict(
assigner=dict(
pos_iou_thr=0.65, neg_iou_thr=0.65, min_pos_iou=0.65),
sampler=dict(num=256))),
test_cfg=dict(rcnn=dict(score_thr=1e-3)))
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadProposals', num_max_proposals=300),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadProposals', num_max_proposals=300),
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='ToTensor', keys=['proposals']),
dict(
type='ToDataContainer',
fields=[dict(key='proposals', stack=False)]),
dict(type='Collect', keys=['img', 'proposals']),
])
]
data = dict(
train=dict(
proposal_file=data_root +
'proposals/crpn_r50_caffe_fpn_1x_train2017.pkl',
pipeline=train_pipeline),
val=dict(
proposal_file=data_root +
'proposals/crpn_r50_caffe_fpn_1x_val2017.pkl',
pipeline=test_pipeline),
test=dict(
proposal_file=data_root +
'proposals/crpn_r50_caffe_fpn_1x_val2017.pkl',
pipeline=test_pipeline))
optimizer_config = dict(
_delete_=True, grad_clip=dict(max_norm=35, norm_type=2))
mmdet/.mim/configs/cascade_rpn/crpn_faster_rcnn_r50_caffe_fpn_1x_coco.py 0 → 100644
_base_ = '../faster_rcnn/faster_rcnn_r50_caffe_fpn_1x_coco.py'
rpn_weight = 0.7
model = dict(
rpn_head=dict(
_delete_=True,
type='CascadeRPNHead',
num_stages=2,
stages=[
dict(
type='StageCascadeRPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[1.0],
strides=[4, 8, 16, 32, 64]),
adapt_cfg=dict(type='dilation', dilation=3),
bridged_feature=True,
sampling=False,
with_cls=False,
reg_decoded_bbox=True,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.5, 0.5)),
loss_bbox=dict(
type='IoULoss', linear=True,
loss_weight=10.0 * rpn_weight)),
dict(
type='StageCascadeRPNHead',
in_channels=256,
feat_channels=256,
adapt_cfg=dict(type='offset'),
bridged_feature=False,
sampling=True,
with_cls=True,
reg_decoded_bbox=True,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=(.0, .0, .0, .0),
target_stds=(0.05, 0.05, 0.1, 0.1)),
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
loss_weight=1.0 * rpn_weight),
loss_bbox=dict(
type='IoULoss', linear=True,
loss_weight=10.0 * rpn_weight))
]),
roi_head=dict(
bbox_head=dict(
bbox_coder=dict(target_stds=[0.04, 0.04, 0.08, 0.08]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.5),
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='RegionAssigner', center_ratio=0.2, ignore_ratio=0.5),
allowed_border=-1,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
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=-1,
pos_weight=-1,
debug=False)
],
rpn_proposal=dict(max_per_img=300, nms=dict(iou_threshold=0.8)),
rcnn=dict(
assigner=dict(
pos_iou_thr=0.65, neg_iou_thr=0.65, min_pos_iou=0.65),
sampler=dict(type='RandomSampler', num=256))),
test_cfg=dict(
rpn=dict(max_per_img=300, nms=dict(iou_threshold=0.8)),
rcnn=dict(score_thr=1e-3)))
optimizer_config = dict(
_delete_=True, grad_clip=dict(max_norm=35, norm_type=2))
mmdet/.mim/configs/cascade_rpn/crpn_r50_caffe_fpn_1x_coco.py 0 → 100644
_base_ = '../rpn/rpn_r50_caffe_fpn_1x_coco.py'
model = dict(
rpn_head=dict(
_delete_=True,
type='CascadeRPNHead',
num_stages=2,
stages=[
dict(
type='StageCascadeRPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[1.0],
strides=[4, 8, 16, 32, 64]),
adapt_cfg=dict(type='dilation', dilation=3),
bridged_feature=True,
sampling=False,
with_cls=False,
reg_decoded_bbox=True,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.5, 0.5)),
loss_bbox=dict(type='IoULoss', linear=True, loss_weight=10.0)),
dict(
type='StageCascadeRPNHead',
in_channels=256,
feat_channels=256,
adapt_cfg=dict(type='offset'),
bridged_feature=False,
sampling=True,
with_cls=True,
reg_decoded_bbox=True,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=(.0, .0, .0, .0),
target_stds=(0.05, 0.05, 0.1, 0.1)),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True,
loss_weight=1.0),
loss_bbox=dict(type='IoULoss', linear=True, loss_weight=10.0))
]),
train_cfg=dict(rpn=[
dict(
assigner=dict(
type='RegionAssigner', center_ratio=0.2, ignore_ratio=0.5),
allowed_border=-1,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.3,
ignore_iof_thr=-1,
iou_calculator=dict(type='BboxOverlaps2D')),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False)
]),
test_cfg=dict(
rpn=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.8),
min_bbox_size=0)))
optimizer_config = dict(
_delete_=True, grad_clip=dict(max_norm=35, norm_type=2))
mmdet/.mim/configs/cascade_rpn/metafile.yml 0 → 100644
Collections:
- Name: Cascade RPN
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x V100 GPUs
Architecture:
- Cascade RPN
- FPN
- ResNet
Paper:
URL: https://arxiv.org/abs/1909.06720
Title: 'Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution'
README: configs/cascade_rpn/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.8.0/mmdet/models/dense_heads/cascade_rpn_head.py#L538
Version: v2.8.0
Models:
- Name: crpn_fast_rcnn_r50_caffe_fpn_1x_coco
In Collection: Cascade RPN
Config: configs/cascade_rpn/crpn_fast_rcnn_r50_caffe_fpn_1x_coco.py
Metadata:
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 39.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/cascade_rpn/crpn_fast_rcnn_r50_caffe_fpn_1x_coco/crpn_fast_rcnn_r50_caffe_fpn_1x_coco-cb486e66.pth
- Name: crpn_faster_rcnn_r50_caffe_fpn_1x_coco
In Collection: Cascade RPN
Config: configs/cascade_rpn/crpn_faster_rcnn_r50_caffe_fpn_1x_coco.py
Metadata:
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.4
Weights: https://download.openmmlab.com/mmdetection/v2.0/cascade_rpn/crpn_faster_rcnn_r50_caffe_fpn_1x_coco/crpn_faster_rcnn_r50_caffe_fpn_1x_coco-c8283cca.pth
mmdet/.mim/configs/centernet/README.md 0 → 100644
# CenterNet
> [Objects as Points](https://arxiv.org/abs/1904.07850)
<!-- [ALGORITHM] -->
## Abstract
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point --- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors. CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with 28.1% AP at 142 FPS, 37.4% AP at 52 FPS, and 45.1% AP with multi-scale testing at 1.4 FPS. We use the same approach to estimate 3D bounding box in the KITTI benchmark and human pose on the COCO keypoint dataset. Our method performs competitively with sophisticated multi-stage methods and runs in real-time.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143873810-85ffa6e7-915b-46a4-9b8f-709e5d7700bb.png"/>
</div>
## Results and Models
| Backbone | DCN | Mem (GB) | Box AP | Flip box AP| Config | Download |
| :-------------: | :--------: |:----------------: | :------: | :------------: | :----: | :----: |
| ResNet-18 | N | 3.45 | 25.9 | 27.3 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/centernet/centernet_resnet18_140e_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_140e_coco/centernet_resnet18_140e_coco_20210705_093630-bb5b3bf7.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_140e_coco/centernet_resnet18_140e_coco_20210705_093630.log.json) |
| ResNet-18 | Y | 3.47 | 29.5 | 30.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/centernet/centernet_resnet18_dcnv2_140e_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_dcnv2_140e_coco/centernet_resnet18_dcnv2_140e_coco_20210702_155131-c8cd631f.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_dcnv2_140e_coco/centernet_resnet18_dcnv2_140e_coco_20210702_155131.log.json) |
Note:
- Flip box AP setting is single-scale and `flip=True`.
- Due to complex data enhancement, we find that the performance is unstable and may fluctuate by about 0.4 mAP. mAP 29.4 ~ 29.8 is acceptable in ResNet-18-DCNv2.
- Compared to the source code, we refer to [CenterNet-Better](https://github.com/FateScript/CenterNet-better), and make the following changes
- fix wrong image mean and variance in image normalization to be compatible with the pre-trained backbone.
- Use SGD rather than ADAM optimizer and add warmup and grad clip.
- Use DistributedDataParallel as other models in MMDetection rather than using DataParallel.
## Citation
```latex
@article{zhou2019objects,
title={Objects as Points},
author={Zhou, Xingyi and Wang, Dequan and Kr{\"a}henb{\"u}hl, Philipp},
booktitle={arXiv preprint arXiv:1904.07850},
year={2019}
}
```
mmdet/.mim/configs/centernet/centernet_resnet18_140e_coco.py 0 → 100644
_base_ = './centernet_resnet18_dcnv2_140e_coco.py'
model = dict(neck=dict(use_dcn=False))
mmdet/.mim/configs/centernet/centernet_resnet18_dcnv2_140e_coco.py 0 → 100644
_base_ = [
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
type='CenterNet',
backbone=dict(
type='ResNet',
depth=18,
norm_eval=False,
norm_cfg=dict(type='BN'),
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18')),
neck=dict(
type='CTResNetNeck',
in_channel=512,
num_deconv_filters=(256, 128, 64),
num_deconv_kernels=(4, 4, 4),
use_dcn=True),
bbox_head=dict(
type='CenterNetHead',
num_classes=80,
in_channel=64,
feat_channel=64,
loss_center_heatmap=dict(type='GaussianFocalLoss', loss_weight=1.0),
loss_wh=dict(type='L1Loss', loss_weight=0.1),
loss_offset=dict(type='L1Loss', loss_weight=1.0)),
train_cfg=None,
test_cfg=dict(topk=100, local_maximum_kernel=3, max_per_img=100))
# We fixed the incorrect img_norm_cfg problem in the source code.
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', to_float32=True, color_type='color'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(
type='RandomCenterCropPad',
crop_size=(512, 512),
ratios=(0.6, 0.7, 0.8, 0.9, 1.0, 1.1, 1.2, 1.3),
mean=[0, 0, 0],
std=[1, 1, 1],
to_rgb=True,
test_pad_mode=None),
dict(type='Resize', img_scale=(512, 512), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
dict(type='LoadImageFromFile', to_float32=True),
dict(
type='MultiScaleFlipAug',
scale_factor=1.0,
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(
type='RandomCenterCropPad',
ratios=None,
border=None,
mean=[0, 0, 0],
std=[1, 1, 1],
to_rgb=True,
test_mode=True,
test_pad_mode=['logical_or', 31],
test_pad_add_pix=1),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
meta_keys=('filename', 'ori_shape', 'img_shape', 'pad_shape',
'scale_factor', 'flip', 'flip_direction',
'img_norm_cfg', 'border'),
keys=['img'])
])
]
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
# Use RepeatDataset to speed up training
data = dict(
samples_per_gpu=16,
workers_per_gpu=4,
train=dict(
_delete_=True,
type='RepeatDataset',
times=5,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline)),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
# Based on the default settings of modern detectors, the SGD effect is better
# than the Adam in the source code, so we use SGD default settings and
# if you use adam+lr5e-4, the map is 29.1.
optimizer_config = dict(
_delete_=True, grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
# Based on the default settings of modern detectors, we added warmup settings.
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[18, 24]) # the real step is [18*5, 24*5]
runner = dict(max_epochs=28) # the real epoch is 28*5=140
mmdet/.mim/configs/centernet/metafile.yml 0 → 100644
Collections:
- Name: CenterNet
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x TITANXP GPUs
Architecture:
- ResNet
Paper:
URL: https://arxiv.org/abs/1904.07850
Title: 'Objects as Points'
README: configs/centernet/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.13.0/mmdet/models/detectors/centernet.py#L10
Version: v2.13.0
Models:
- Name: centernet_resnet18_dcnv2_140e_coco
In Collection: CenterNet
Config: configs/centernet/centernet_resnet18_dcnv2_140e_coco.py
Metadata:
Batch Size: 128
Training Memory (GB): 3.47
Epochs: 140
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 29.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_dcnv2_140e_coco/centernet_resnet18_dcnv2_140e_coco_20210702_155131-c8cd631f.pth
- Name: centernet_resnet18_140e_coco
In Collection: CenterNet
Config: configs/centernet/centernet_resnet18_140e_coco.py
Metadata:
Batch Size: 128
Training Memory (GB): 3.45
Epochs: 140
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 25.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_140e_coco/centernet_resnet18_140e_coco_20210705_093630-bb5b3bf7.pth
mmdet/.mim/configs/centripetalnet/README.md 0 → 100644
# CentripetalNet
> [CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection](https://arxiv.org/abs/2003.09119)
<!-- [ALGORITHM] -->
## Abstract
Keypoint-based detectors have achieved pretty-well performance. However, incorrect keypoint matching is still widespread and greatly affects the performance of the detector. In this paper, we propose CentripetalNet which uses centripetal shift to pair corner keypoints from the same instance. CentripetalNet predicts the position and the centripetal shift of the corner points and matches corners whose shifted results are aligned. Combining position information, our approach matches corner points more accurately than the conventional embedding approaches do. Corner pooling extracts information inside the bounding boxes onto the border. To make this information more aware at the corners, we design a cross-star deformable convolution network to conduct feature adaption. Furthermore, we explore instance segmentation on anchor-free detectors by equipping our CentripetalNet with a mask prediction module. On MS-COCO test-dev, our CentripetalNet not only outperforms all existing anchor-free detectors with an AP of 48.0% but also achieves comparable performance to the state-of-the-art instance segmentation approaches with a 40.2% MaskAP.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143873955-42804e0e-3638-4c5b-8bf4-ac8133bbcdc8.png"/>
</div>
## Results and Models
| Backbone | Batch Size | Step/Total Epochs | Mem (GB) | Inf time (fps) | box AP | Config | Download |
| :-------------: | :--------: |:----------------: | :------: | :------------: | :----: | :------: | :--------: |
| HourglassNet-104 | [16 x 6](./centripetalnet_hourglass104_mstest_16x6_210e_coco.py) | 190/210 | 16.7 | 3.7 | 44.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco/centripetalnet_hourglass104_mstest_16x6_210e_coco_20200915_204804-3ccc61e5.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco/centripetalnet_hourglass104_mstest_16x6_210e_coco_20200915_204804.log.json) |
Note:
- TTA setting is single-scale and `flip=True`.
- The model we released is the best checkpoint rather than the latest checkpoint (box AP 44.8 vs 44.6 in our experiment).
## Citation
```latex
@InProceedings{Dong_2020_CVPR,
author = {Dong, Zhiwei and Li, Guoxuan and Liao, Yue and Wang, Fei and Ren, Pengju and Qian, Chen},
title = {CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
```
mmdet/.mim/configs/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco.py 0 → 100644
_base_ = [
'../_base_/default_runtime.py', '../_base_/datasets/coco_detection.py'
]
# model settings
model = dict(
type='CornerNet',
backbone=dict(
type='HourglassNet',
downsample_times=5,
num_stacks=2,
stage_channels=[256, 256, 384, 384, 384, 512],
stage_blocks=[2, 2, 2, 2, 2, 4],
norm_cfg=dict(type='BN', requires_grad=True)),
neck=None,
bbox_head=dict(
type='CentripetalHead',
num_classes=80,
in_channels=256,
num_feat_levels=2,
corner_emb_channels=0,
loss_heatmap=dict(
type='GaussianFocalLoss', alpha=2.0, gamma=4.0, loss_weight=1),
loss_offset=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1),
loss_guiding_shift=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=0.05),
loss_centripetal_shift=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=1)),
# training and testing settings
train_cfg=None,
test_cfg=dict(
corner_topk=100,
local_maximum_kernel=3,
distance_threshold=0.5,
score_thr=0.05,
max_per_img=100,
nms=dict(type='soft_nms', iou_threshold=0.5, method='gaussian')))
# data settings
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', to_float32=True),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(
type='RandomCenterCropPad',
crop_size=(511, 511),
ratios=(0.6, 0.7, 0.8, 0.9, 1.0, 1.1, 1.2, 1.3),
test_mode=False,
test_pad_mode=None,
**img_norm_cfg),
dict(type='Resize', img_scale=(511, 511), keep_ratio=False),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile', to_float32=True),
dict(
type='MultiScaleFlipAug',
scale_factor=1.0,
flip=True,
transforms=[
dict(type='Resize'),
dict(
type='RandomCenterCropPad',
crop_size=None,
ratios=None,
border=None,
test_mode=True,
test_pad_mode=['logical_or', 127],
**img_norm_cfg),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(
type='Collect',
keys=['img'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'pad_shape',
'scale_factor', 'flip', 'img_norm_cfg', 'border')),
])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=3,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='Adam', lr=0.0005)
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=[190])
runner = dict(type='EpochBasedRunner', max_epochs=210)
mmdet/.mim/configs/centripetalnet/metafile.yml 0 → 100644
Collections:
- Name: CentripetalNet
Metadata:
Training Data: COCO
Training Techniques:
- Adam
Training Resources: 16x V100 GPUs
Architecture:
- Corner Pooling
- Stacked Hourglass Network
Paper:
URL: https://arxiv.org/abs/2003.09119
Title: 'CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection'
README: configs/centripetalnet/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.5.0/mmdet/models/detectors/cornernet.py#L9
Version: v2.5.0
Models:
- Name: centripetalnet_hourglass104_mstest_16x6_210e_coco
In Collection: CentripetalNet
Config: configs/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco.py
Metadata:
Batch Size: 96
Training Memory (GB): 16.7
inference time (ms/im):
- value: 270.27
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (800, 1333)
Epochs: 210
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 44.8
Weights: https://download.openmmlab.com/mmdetection/v2.0/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco/centripetalnet_hourglass104_mstest_16x6_210e_coco_20200915_204804-3ccc61e5.pth
mmdet/.mim/configs/cityscapes/README.md 0 → 100644
# Cityscapes
> [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://arxiv.org/abs/1604.01685)
<!-- [DATASET] -->
## Abstract
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes.
To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations; 20000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143874154-db4484a5-9211-41f6-852a-b7f0a8c9ec26.png"/>
</div>
## 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)
- COCO pre-trained weights are used to initialize.
- A conversion [script](../../tools/dataset_converters/cityscapes.py) is provided to convert Cityscapes into COCO format. Please refer to [install.md](../../docs/1_exist_data_model.md#prepare-datasets) for details.
- `CityscapesDataset` implemented three evaluation methods. `bbox` and `segm` are standard COCO bbox/mask AP. `cityscapes` is the cityscapes dataset official evaluation, which may be slightly higher than COCO.
### Faster R-CNN
| Backbone | Style | Lr schd | Scale | Mem (GB) | Inf time (fps) | box AP | Config | Download |
| :-------------: | :-----: | :-----: | :---: | :------: | :------------: | :----: | :------: | :--------: |
| R-50-FPN | pytorch | 1x | 800-1024 | 5.2 | - | 40.3 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes_20200502-829424c0.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes_20200502_114915.log.json) |
### Mask R-CNN
| Backbone | Style | Lr schd | Scale | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
| :-------------: | :-----: | :-----: | :------: | :------: | :------------: | :----: | :-----: | :------: | :------: |
| R-50-FPN | pytorch | 1x | 800-1024 | 5.3 | - | 40.9 | 36.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes/mask_rcnn_r50_fpn_1x_cityscapes_20201211_133733-d2858245.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes/mask_rcnn_r50_fpn_1x_cityscapes_20201211_133733.log.json) |
## Citation
```latex
@inproceedings{Cordts2016Cityscapes,
title={The Cityscapes Dataset for Semantic Urban Scene Understanding},
author={Cordts, Marius and Omran, Mohamed and Ramos, Sebastian and Rehfeld, Timo and Enzweiler, Markus and Benenson, Rodrigo and Franke, Uwe and Roth, Stefan and Schiele, Bernt},
booktitle={Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2016}
}
```
mmdet/.mim/configs/cityscapes/faster_rcnn_r50_fpn_1x_cityscapes.py 0 → 100644
_base_ = [
'../_base_/models/faster_rcnn_r50_fpn.py',
'../_base_/datasets/cityscapes_detection.py',
'../_base_/default_runtime.py'
]
model = dict(
backbone=dict(init_cfg=None),
roi_head=dict(
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=8,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
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))))
# 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=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
# [7] yields higher performance than [6]
step=[7])
runner = dict(
type='EpochBasedRunner', max_epochs=8) # actual epoch = 8 * 8 = 64
log_config = dict(interval=100)
# For better, more stable performance initialize from COCO
load_from = 'https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth' # noqa
mmdet/datasets/pipelines/transforms.py 0 → 100644
This diff could not be displayed because it is too large.
Styling with Markdown is supported
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!