Skip to content

GitLab

Commit 57f6da5c authored by bailuo's avatar bailuo
Browse files

readme

parents
Hide whitespace changes
Inline Side-by-side
Showing with 2965 additions and 0 deletions
configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_1x.py 0 → 100644
View file @ 57f6da5c
# model settings
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
gcb=dict(ratio=1. / 4., ),
stage_with_gcb=(False, True, True, True)),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r4_gcb_c3-c5_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gcnet/mask_rcnn_r4_gcb_c3-c5_r50_fpn_syncbn_1x.py 0 → 100644
View file @ 57f6da5c
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
gcb=dict(ratio=1. / 4., ),
stage_with_gcb=(False, True, True, True),
norm_eval=False,
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r4_gcb_c3-c5_r50_fpn_syncbn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gcnet/mask_rcnn_r50_fpn_sbn_1x.py 0 → 100644
View file @ 57f6da5c
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
norm_eval=False,
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_sbn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/ghm/README.md 0 → 100644
View file @ 57f6da5c
# Gradient Harmonized Single-stage Detector
## Introduction
```
@inproceedings{li2019gradient,
title={Gradient Harmonized Single-stage Detector},
author={Li, Buyu and Liu, Yu and Wang, Xiaogang},
booktitle={AAAI Conference on Artificial Intelligence},
year={2019}
}
```
## Results and Models
| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
| :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :------: |
| R-50-FPN | pytorch | 1x | 3.9 | 0.500 | 9.4 | 36.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_r50_fpn_1x_20190608-b9aa5862.pth) |
| R-101-FPN | pytorch | 1x | 5.8 | 0.625 | 8.5 | 39.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_r101_fpn_1x_20190608-b885b74a.pth) |
| X-101-32x4d-FPN | pytorch | 1x | 7.0 | 0.818 | 7.6 | 40.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_x101_32x4d_fpn_1x_20190608-ed295d22.pth) |
| X-101-64x4d-FPN | pytorch | 1x | 9.9 | 1.191 | 6.1 | 41.6 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_x101_64x4d_fpn_1x_20190608-7f2037ce.pth) |
\ No newline at end of file
configs/ghm/retinanet_ghm_r50_fpn_1x.py 0 → 100644
View file @ 57f6da5c
# model settings
model = dict(
type='RetinaNet',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5),
bbox_head=dict(
type='RetinaHead',
num_classes=81,
in_channels=256,
stacked_convs=4,
feat_channels=256,
octave_base_scale=4,
scales_per_octave=3,
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[8, 16, 32, 64, 128],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='GHMC',
bins=30,
momentum=0.75,
use_sigmoid=True,
loss_weight=1.0),
loss_bbox=dict(
type='GHMR', mu=0.02, bins=10, momentum=0.7, loss_weight=10.0)))
# 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_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ghm'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gn+ws/README.md 0 → 100644
View file @ 57f6da5c
# Weight Standardization
## Introduction
```
@article{weightstandardization,
author = {Siyuan Qiao and Huiyu Wang and Chenxi Liu and Wei Shen and Alan Yuille},
title = {Weight Standardization},
journal = {arXiv preprint arXiv:1903.10520},
year = {2019},
}
```
## Results and Models
Faster R-CNN
| Backbone | Style | Normalization | Lr schd | box AP | mask AP | Download |
|:---------:|:-------:|:-------------:|:-------:|:------:|:-------:|:--------:|
| R-50-FPN | pytorch | GN | 1x | 37.8 | - | - |
| R-50-FPN | pytorch | GN+WS | 1x | 38.9 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/faster_rcnn_r50_fpn_gn_ws_1x_20190418-935d00b6.pth) |
| R-101-FPN | pytorch | GN | 1x | 39.8 | - | - |
| R-101-FPN | pytorch | GN+WS | 1x | 41.4 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/faster_rcnn_r101_fpn_gn_ws_1x_20190419-728705ec.pth) |
| X-50-32x4d-FPN | pytorch | GN | 1x | 36.5 | - | - |
| X-50-32x4d-FPN | pytorch | GN+WS | 1x | 39.9 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/faster_rcnn_x50_32x4d_fpn_gn_ws_1x_20190419-4e61072b.pth) |
| X-101-32x4d-FPN | pytorch | GN | 1x | 33.2 | - | - |
| X-101-32x4d-FPN | pytorch | GN+WS | 1x | 41.8 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/faster_rcnn_x101_32x4d_fpn_gn_ws_1x_20190419-c78e5583.pth) |
Mask R-CNN
| Backbone | Style | Normalization | Lr schd | box AP | mask AP | Download |
|:---------:|:-------:|:-------------:|:-------:|:------:|:-------:|:--------:|
| R-50-FPN | pytorch | GN | 2x | 39.9 | 36.0 | - |
| R-50-FPN | pytorch | GN+WS | 2x | 40.3 | 36.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_r50_fpn_gn_ws_2x_20190419-9ec97bbb.pth) |
| R-101-FPN | pytorch | GN | 2x | 41.6 | 37.3 | - |
| R-101-FPN | pytorch | GN+WS | 2x | 42.0 | 37.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_r101_fpn_gn_ws_2x_20190419-bc7399a6.pth) |
| X-50-32x4d-FPN | pytorch | GN | 2x | 39.2 | 35.5 | - |
| X-50-32x4d-FPN | pytorch | GN+WS | 2x | 40.7 | 36.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_x50_32x4d_fpn_gn_ws_2x_20190419-2110205e.pth) |
| X-101-32x4d-FPN | pytorch | GN | 2x | 36.4 | 33.1 | - |
| X-101-32x4d-FPN | pytorch | GN+WS | 2x | 42.1 | 37.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_x101_32x4d_fpn_gn_ws_2x_20190419-7777b15f.pth) |
| R-50-FPN | pytorch | GN | 20-23-24e | 40.6 | 36.6 | - |
| R-50-FPN | pytorch | GN+WS | 20-23-24e | 41.1 | 37.0 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_r50_fpn_gn_ws_20_23_24e_20190425-1d9e499e.pth) |
| R-101-FPN | pytorch | GN | 20-23-24e | 42.3 | 38.1 | - |
| R-101-FPN | pytorch | GN+WS | 20-23-24e | 43.0 | 38.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_r101_fpn_gn_ws_20_23_24e_20190425-66cb3792.pth) |
| X-50-32x4d-FPN | pytorch | GN | 20-23-24e | 39.6 | 35.9 | - |
| X-50-32x4d-FPN | pytorch | GN+WS | 20-23-24e | 41.9 | 37.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_x50_32x4d_fpn_gn_ws_20_23_24e_20190425-d01e2200.pth) |
| X-101-32x4d-FPN | pytorch | GN | 20-23-24e | 36.6 | 33.4 | - |
| X-101-32x4d-FPN | pytorch | GN+WS | 20-23-24e | 43.4 | 38.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ws/mask_rcnn_x101_32x4d_fpn_gn_ws_20_23_24e_20190425-1ff3e5b2.pth) |
Note:
- GN+WS requires about 5% more memory than GN, and it is only 5% slower than GN.
- In the paper, a 20-23-24e lr schedule is used instead of 2x.
- The X-50-GN and X-101-GN pretrained models are also shared by the authors.
\ No newline at end of file
configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py 0 → 100644
View file @ 57f6da5c
# model settings
conv_cfg = dict(type='ConvWS')
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='FasterRCNN',
pretrained='open-mmlab://jhu/resnet50_gn_ws',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/faster_rcnn_r50_fpn_gn_ws_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_20_23_24e.py 0 → 100644
View file @ 57f6da5c
# model settings
conv_cfg = dict(type='ConvWS')
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://jhu/resnet50_gn_ws',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[20, 23])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_gn_ws_20_23_24e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gn+ws/mask_rcnn_r50_fpn_gn_ws_2x.py 0 → 100644
View file @ 57f6da5c
# model settings
conv_cfg = dict(type='ConvWS')
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://jhu/resnet50_gn_ws',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_gn_ws_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws_2x.py 0 → 100644
View file @ 57f6da5c
# model settings
conv_cfg = dict(type='ConvWS')
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://jhu/resnext101_32x4d_gn_ws',
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_x101_32x4d_fpn_gn_ws_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gn/README.md 0 → 100644
View file @ 57f6da5c
# Group Normalization
## Introduction
```
@inproceedings{wu2018group,
title={Group Normalization},
author={Wu, Yuxin and He, Kaiming},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
year={2018}
}
```
## Results and Models
| Backbone | model | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
|:-------------:|:----------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
| R-50-FPN (d) | Mask R-CNN | 2x | 7.2 | 0.806 | 5.4 | 39.8 | 36.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/gn/mask_rcnn_r50_fpn_gn_2x_20180113-86832cf2.pth) |
| R-50-FPN (d) | Mask R-CNN | 3x | 7.2 | 0.806 | 5.4 | 40.1 | 36.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/gn/mask_rcnn_r50_fpn_gn_3x_20180113-8e82f48d.pth) |
| R-101-FPN (d) | Mask R-CNN | 2x | 9.9 | 0.970 | 4.8 | 41.5 | 37.0 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/gn/mask_rcnn_r101_fpn_gn_2x_20180113-9598649c.pth) |
| R-101-FPN (d) | Mask R-CNN | 3x | 9.9 | 0.970 | 4.8 | 41.6 | 37.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/gn/mask_rcnn_r101_fpn_gn_3x_20180113-a14ffb96.pth) |
| R-50-FPN (c) | Mask R-CNN | 2x | 7.2 | 0.806 | 5.4 | 39.7 | 35.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/gn/mask_rcnn_r50_fpn_gn_contrib_2x_20180113-ec93305c.pth) |
| R-50-FPN (c) | Mask R-CNN | 3x | 7.2 | 0.806 | 5.4 | 40.0 | 36.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/gn/mask_rcnn_r50_fpn_gn_contrib_3x_20180113-9d230cab.pth) |
**Notes:**
- (d) means pretrained model converted from Detectron, and (c) means the contributed model pretrained by [@thangvubk](https://github.com/thangvubk).
- The `3x` schedule is epoch [28, 34, 36].
- **Memory, Train/Inf time is outdated.**
\ No newline at end of file
configs/gn/mask_rcnn_r101_fpn_gn_2x.py 0 → 100644
View file @ 57f6da5c
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://detectron/resnet101_gn',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
norm_cfg=norm_cfg),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
norm_cfg=norm_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
norm_cfg=norm_cfg,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r101_fpn_gn_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gn/mask_rcnn_r50_fpn_gn_2x.py 0 → 100644
View file @ 57f6da5c
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://detectron/resnet50_gn',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
norm_cfg=norm_cfg),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
norm_cfg=norm_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
norm_cfg=norm_cfg,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_gn_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py 0 → 100644
View file @ 57f6da5c
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://contrib/resnet50_gn',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
norm_cfg=norm_cfg),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5,
norm_cfg=norm_cfg),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
norm_cfg=norm_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
norm_cfg=norm_cfg,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_gn_contrib_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/grid_rcnn/README.md 0 → 100644
View file @ 57f6da5c
# Grid R-CNN
## Introduction
```
@inproceedings{lu2019grid,
title={Grid r-cnn},
author={Lu, Xin and Li, Buyu and Yue, Yuxin and Li, Quanquan and Yan, Junjie},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2019}
}
@article{lu2019grid,
title={Grid R-CNN Plus: Faster and Better},
author={Lu, Xin and Li, Buyu and Yue, Yuxin and Li, Quanquan and Yan, Junjie},
journal={arXiv preprint arXiv:1906.05688},
year={2019}
}
```
## Results and Models
| Backbone | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
|:-----------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
| R-50 | 2x | 4.8 | 1.172 | 10.9 | 40.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/grid_rcnn/grid_rcnn_gn_head_r50_fpn_2x_20190619-5b29cf9d.pth) |
| R-101 | 2x | 6.7 | 1.214 | 10.0 | 41.7 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/grid_rcnn/grid_rcnn_gn_head_r101_fpn_2x_20190619-a4b61645.pth) |
| X-101-32x4d | 2x | 8.0 | 1.335 | 8.5 | 43.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/grid_rcnn/grid_rcnn_gn_head_x101_32x4d_fpn_2x_20190619-0bbfd87a.pth) |
| X-101-64x4d | 2x | 10.9 | 1.753 | 6.4 | 43.1 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/grid_rcnn/grid_rcnn_gn_head_x101_64x4d_fpn_2x_20190619-8f4e20bb.pth) |
**Notes:**
- All models are trained with 8 GPUs instead of 32 GPUs in the original paper.
- The warming up lasts for 1 epoch and `2x` here indicates 25 epochs.
configs/grid_rcnn/grid_rcnn_gn_head_r50_fpn_2x.py 0 → 100644
View file @ 57f6da5c
# model settings
model = dict(
type='GridRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
with_reg=False,
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False),
grid_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
grid_head=dict(
type='GridHead',
grid_points=9,
num_convs=8,
in_channels=256,
point_feat_channels=64,
norm_cfg=dict(type='GN', num_groups=36),
loss_grid=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=15)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_radius=1,
pos_weight=-1,
max_num_grid=192,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.03, nms=dict(type='nms', iou_thr=0.3), max_per_img=100))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=3665,
warmup_ratio=1.0 / 80,
step=[17, 23])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 25
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/grid_rcnn_gn_head_r50_fpn_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/grid_rcnn/grid_rcnn_gn_head_x101_32x4d_fpn_2x.py 0 → 100644
View file @ 57f6da5c
# model settings
model = dict(
type='GridRCNN',
pretrained='open-mmlab://resnext101_32x4d',
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
with_reg=False,
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False),
grid_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
grid_head=dict(
type='GridHead',
grid_points=9,
num_convs=8,
in_channels=256,
point_feat_channels=64,
norm_cfg=dict(type='GN', num_groups=36),
loss_grid=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=15)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_radius=1,
pos_weight=-1,
max_num_grid=192,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.03, nms=dict(type='nms', iou_thr=0.3), max_per_img=100))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=3665,
warmup_ratio=1.0 / 80,
step=[17, 23])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 25
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/grid_rcnn_gn_head_x101_32x4d_fpn_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/guided_anchoring/README.md 0 → 100644
View file @ 57f6da5c
# Region Proposal by Guided Anchoring
## Introduction
We provide config files to reproduce the results in the CVPR 2019 paper for [Region Proposal by Guided Anchoring](https://arxiv.org/abs/1901.03278).
```
@inproceedings{wang2019region,
title={Region Proposal by Guided Anchoring},
author={Jiaqi Wang and Kai Chen and Shuo Yang and Chen Change Loy and Dahua Lin},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
year={2019}
}
```
## Results and Models
The results on COCO 2017 val is shown in the below table. (results on test-dev are usually slightly higher than val).
| Method | Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | AR 1000 | Download |
| :----: | :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :-----: | :--------------------------------------------------------------------------------------------------------------------------------------------: |
| GA-RPN | R-50-FPN | caffe | 1x | 5.0 | 0.55 | 13.3 | 68.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_rpn_r50_caffe_fpn_1x_20190513-95e91886.pth) |
| GA-RPN | R-101-FPN | caffe | 1x | 7.1 | 0.66 | 9.8 | 69.6 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_rpn_r101_caffe_fpn_1x_20190523-91e0b817.pth) |
| GA-RPN | X-101-32x4d-FPN | pytorch | 1x | 8.5 | 0.88 | 8.5 | 70.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x_20190523-a60df28c.pth) |
| GA-RPN | X-101-64x4d-FPN | pytorch | 1x | 11.4 | 1.24 | 6.5 | 70.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_rpn_x101_64x4d_fpn_1x_20190523-9f2449ba.pth) |
| Method | Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
| :------------: | :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :--------------------------------------------------------------------------------------------------------------------------------------------------: |
| GA-Fast RCNN | R-50-FPN | caffe | 1x | 3.3 | 0.23 | 14.9 | 39.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_fast_r50_caffe_fpn_1x_20190513-c5af9f8b.pth) |
| GA-Faster RCNN | R-50-FPN | caffe | 1x | 5.1 | 0.64 | 9.6 | 39.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_faster_r50_caffe_fpn_1x_20190513-a52b31fa.pth) |
| GA-Faster RCNN | R-101-FPN | caffe | 1x | 7.3 | 0.75 | 8.0 | 41.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_faster_r101_caffe_fpn_1x_20190523-9a711ec5.pth) |
| GA-Faster RCNN | X-101-32x4d-FPN | pytorch | 1x | 8.7 | 0.97 | 7.1 | 42.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_faster_x101_32x4d_fpn_1x_20190523-8dc3e59a.pth) |
| GA-Faster RCNN | X-101-64x4d-FPN | pytorch | 1x | 11.6 | 1.33 | 5.7 | 43.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_faster_x101_64x4d_fpn_1x_20190523-a8589c97.pth) |
| GA-RetinaNet | R-50-FPN | caffe | 1x | 3.2 | 0.50 | 10.7 | 37.0 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x_20190513-29905101.pth) |
| GA-RetinaNet | R-101-FPN | caffe | 1x | 5.3 | 0.63 | 8.5 | 38.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_retinanet_r101_caffe_fpn_1x_20190523-792ad63d.pth) |
| GA-RetinaNet | X-101-32x4d-FPN | pytorch | 1x | 6.7 | 0.87 | 7.5 | 40.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x_20190523-4ec3f13c.pth) |
| GA-RetinaNet | X-101-64x4d-FPN | pytorch | 1x | 9.6 | 1.22 | 5.8 | 40.8 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_retinanet_x101_64x4d_fpn_1x_20190523-013d1913.pth) |
- In the Guided Anchoring paper, `score_thr` is set to 0.001 in Fast/Faster RCNN and 0.05 in RetinaNet for both baselines and Guided Anchoring.
\ No newline at end of file
configs/guided_anchoring/ga_fast_r50_caffe_fpn_1x.py 0 → 100644
View file @ 57f6da5c
# model settings
model = dict(
type='FastRCNN',
pretrained='open-mmlab://resnet50_caffe',
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'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
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=1e-3, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadProposals', num_max_proposals=300),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadProposals', num_max_proposals=None),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img', 'proposals']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_train2017.pkl',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_val2017.pkl',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
proposal_file=data_root + 'proposals/ga_rpn_r50_fpn_1x_val2017.pkl',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ga_fast_rcnn_r50_caffe_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/guided_anchoring/ga_faster_r50_caffe_fpn_1x.py 0 → 100644
View file @ 57f6da5c
# model settings
model = dict(
type='FasterRCNN',
pretrained='open-mmlab://resnet50_caffe',
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'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='GARPNHead',
in_channels=256,
feat_channels=256,
octave_base_scale=8,
scales_per_octave=3,
octave_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
anchor_base_sizes=None,
anchoring_means=[.0, .0, .0, .0],
anchoring_stds=[0.07, 0.07, 0.14, 0.14],
target_means=(.0, .0, .0, .0),
target_stds=[0.07, 0.07, 0.11, 0.11],
loc_filter_thr=0.01,
loss_loc=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_shape=dict(type='BoundedIoULoss', beta=0.2, loss_weight=1.0),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
ga_assigner=dict(
type='ApproxMaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
ga_sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
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=-1,
pos_weight=-1,
center_ratio=0.2,
ignore_ratio=0.5,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=300,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=300,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=1e-3, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ga_faster_rcnn_r50_caffe_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment