Skip to content

GitLab

Commit a4372e17 authored by huchen's avatar huchen
Browse files

Merge branch 'hepj_work' into 'main' 

增加conformer代码

See merge request dcutoolkit/deeplearing/dlexamples_new!7
parents 7f99c1c3 142dcf29
Show whitespace changes
Inline Side-by-side
Showing with 1602 additions and 0 deletions
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/default_runtime.py 0 → 100644
View file @ a4372e17
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/cascade_mask_rcnn_r50_fpn.py 0 → 100644
View file @ a4372e17
# model settings
model = dict(
type='CascadeRCNN',
pretrained='torchvision://resnet50',
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'),
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_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,
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_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_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/cascade_rcnn_r50_fpn.py 0 → 100644
View file @ a4372e17
# model settings
model = dict(
type='CascadeRCNN',
pretrained='torchvision://resnet50',
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'),
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_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,
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_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_threshold=0.5),
max_per_img=100)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/fast_rcnn_r50_fpn.py 0 → 100644
View file @ a4372e17
# model settings
model = dict(
type='FastRCNN',
pretrained='torchvision://resnet50',
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'),
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)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/faster_rcnn_r50_caffe_c4.py 0 → 100644
View file @ a4372e17
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='FasterRCNN',
pretrained='open-mmlab://detectron2/resnet50_caffe',
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'),
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_across_levels=False,
nms_pre=12000,
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,
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_across_levels=False,
nms_pre=6000,
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_threshold=0.5),
max_per_img=100)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/faster_rcnn_r50_caffe_dc5.py 0 → 100644
View file @ a4372e17
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='FasterRCNN',
pretrained='open-mmlab://detectron2/resnet50_caffe',
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'),
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_across_levels=False,
nms_pre=12000,
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,
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_across_levels=False,
nms_pre=6000,
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_threshold=0.5),
max_per_img=100)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/faster_rcnn_r50_fpn.py 0 → 100644
View file @ a4372e17
model = dict(
type='FasterRCNN',
pretrained='torchvision://resnet50',
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'),
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_across_levels=False,
nms_pre=2000,
nms_post=1000,
max_num=1000,
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,
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_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_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)
))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/mask_rcnn_r50_caffe_c4.py 0 → 100644
View file @ a4372e17
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://detectron2/resnet50_caffe',
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'),
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_across_levels=False,
nms_pre=12000,
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,
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_across_levels=False,
nms_pre=6000,
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_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/mask_rcnn_r50_fpn.py 0 → 100644
View file @ a4372e17
# 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,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
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_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_across_levels=False,
nms_pre=2000,
nms_post=1000,
max_num=1000,
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,
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_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_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/retinanet_r50_fpn.py 0 → 100644
View file @ a4372e17
# 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,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch'),
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)),
# 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))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/rpn_r50_caffe_c4.py 0 → 100644
View file @ a4372e17
# model settings
model = dict(
type='RPN',
pretrained='open-mmlab://detectron2/resnet50_caffe',
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'),
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_across_levels=False,
nms_pre=12000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/rpn_r50_fpn.py 0 → 100644
View file @ a4372e17
# model settings
model = dict(
type='RPN',
pretrained='torchvision://resnet50',
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'),
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_across_levels=False,
nms_pre=2000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0)))
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/models/ssd300.py 0 → 100644
View file @ a4372e17
# model settings
input_size = 300
model = dict(
type='SingleStageDetector',
pretrained='open-mmlab://vgg16_caffe',
backbone=dict(
type='SSDVGG',
input_size=input_size,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
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])),
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=dict(type='nms', iou_threshold=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200))
cudnn_benchmark = True
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/schedules/schedule_1x.py 0 → 100644
View file @ a4372e17
# 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])
total_epochs = 12
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/schedules/schedule_20e.py 0 → 100644
View file @ a4372e17
# 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])
total_epochs = 20
PyTorch/NLP/Conformer-main/mmdetection/configs/_base_/schedules/schedule_2x.py 0 → 100644
View file @ a4372e17
# 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])
total_epochs = 24
PyTorch/NLP/Conformer-main/mmdetection/configs/faster_rcnn/README.md 0 → 100644
View file @ a4372e17
# Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
## Introduction
[ALGORITHM]
```latex
@article{Ren_2017,
title={Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
publisher={Institute of Electrical and Electronics Engineers (IEEE)},
author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
year={2017},
month={Jun},
}
```
## Results and models
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: |
| R-50-DC5 | caffe | 1x | - | - | 37.2 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/faster_rcnn/faster_rcnn_r50_caffe_dc5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_1x_coco/faster_rcnn_r50_caffe_dc5_1x_coco_20201030_151909-531f0f43.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_1x_coco/faster_rcnn_r50_caffe_dc5_1x_coco_20201030_151909.log.json) |
| R-50-FPN | caffe | 1x | 3.8 | | 37.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_1x_coco/faster_rcnn_r50_caffe_fpn_1x_coco_bbox_mAP-0.378_20200504_180032-c5925ee5.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_1x_coco/faster_rcnn_r50_caffe_fpn_1x_coco_20200504_180032.log.json) |
| R-50-FPN | pytorch | 1x | 4.0 | 21.4 | 37.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130_204655.log.json) |
| R-50-FPN | pytorch | 2x | - | - | 38.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_2x_coco/faster_rcnn_r50_fpn_2x_coco_bbox_mAP-0.384_20200504_210434-a5d8aa15.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_2x_coco/faster_rcnn_r50_fpn_2x_coco_20200504_210434.log.json) |
| R-101-FPN | caffe | 1x | 5.7 | | 39.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r101_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_caffe_fpn_1x_coco/faster_rcnn_r101_caffe_fpn_1x_coco_bbox_mAP-0.398_20200504_180057-b269e9dd.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_caffe_fpn_1x_coco/faster_rcnn_r101_caffe_fpn_1x_coco_20200504_180057.log.json) |
| R-101-FPN | pytorch | 1x | 6.0 | 15.6 | 39.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_1x_coco/faster_rcnn_r101_fpn_1x_coco_20200130-f513f705.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_1x_coco/faster_rcnn_r101_fpn_1x_coco_20200130_204655.log.json) |
| R-101-FPN | pytorch | 2x | - | - | 39.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_2x_coco/faster_rcnn_r101_fpn_2x_coco_bbox_mAP-0.398_20200504_210455-1d2dac9c.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_2x_coco/faster_rcnn_r101_fpn_2x_coco_20200504_210455.log.json) |
| X-101-32x4d-FPN | pytorch | 1x | 7.2 | 13.8 | 41.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_32x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x4d_fpn_1x_coco/faster_rcnn_x101_32x4d_fpn_1x_coco_20200203-cff10310.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x4d_fpn_1x_coco/faster_rcnn_x101_32x4d_fpn_1x_coco_20200203_000520.log.json) |
| X-101-32x4d-FPN | pytorch | 2x | - | - | 41.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_32x4d_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x4d_fpn_2x_coco/faster_rcnn_x101_32x4d_fpn_2x_coco_bbox_mAP-0.412_20200506_041400-64a12c0b.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x4d_fpn_2x_coco/faster_rcnn_x101_32x4d_fpn_2x_coco_20200506_041400.log.json) |
| X-101-64x4d-FPN | pytorch | 1x | 10.3 | 9.4 | 42.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_64x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_1x_coco/faster_rcnn_x101_64x4d_fpn_1x_coco_20200204-833ee192.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_1x_coco/faster_rcnn_x101_64x4d_fpn_1x_coco_20200204_134340.log.json) |
| X-101-64x4d-FPN | pytorch | 2x | - | - | 41.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_64x4d_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_2x_coco/faster_rcnn_x101_64x4d_fpn_2x_coco_20200512_161033-5961fa95.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_2x_coco/faster_rcnn_x101_64x4d_fpn_2x_coco_20200512_161033.log.json) |
## Different regression loss
We trained with R-50-FPN pytorch style backbone for 1x schedule.
| Backbone | Loss type | Mem (GB) | Inf time (fps) | box AP | Config | Download |
| :-------------: | :-------: | :------: | :------------: | :----: | :------: | :--------: |
| R-50-FPN | L1Loss | 4.0 | 21.4 | 37.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130_204655.log.json) |
| R-50-FPN | IoULoss | | | 37.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_iou_1x_coco-fdd207f3.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_iou_1x_coco_20200506_095954.log.json) |
| R-50-FPN | GIoULoss | | | 37.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_giou_1x_coco-0eada910.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_giou_1x_coco_20200505_161120.log.json) |
| R-50-FPN | BoundedIoULoss | | | 37.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco-98ad993b.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco_20200505_160738.log.json) |
## Pre-trained Models
We also train some models with longer schedules and multi-scale training. The users could finetune them for downstream tasks.
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: |
| [R-50-DC5](./faster_rcnn_r50_caffe_dc5_mstrain_1x_coco.py) | caffe | 1x | - | | 37.4 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco_20201028_233851-b33d21b9.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco/faster_rcnn_r50_caffe_dc5_mstrain_1x_coco_20201028_233851.log.json)
| [R-50-DC5](./faster_rcnn_r50_caffe_dc5_mstrain_3x_coco.py) | caffe | 3x | - | | 38.7 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco_20201028_002107-34a53b2c.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco_20201028_002107.log.json)
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py) | caffe | 2x | 4.3 | | 39.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco_bbox_mAP-0.397_20200504_231813-10b2de58.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco_20200504_231813.log.json)
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | caffe | 3x | 4.3 | | 40.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_bbox_mAP-0.398_20200504_163323-30042637.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_20200504_163323.log.json)
We further finetune some pre-trained models on the COCO subsets, which only contain only a few of the 80 categories.
| Backbone | Style | Class name | Pre-traind model | Mem (GB) | box AP | Config | Download |
| ------------------------------------------------------------ | ----- | ------------------ | ------------------------------------------------------------ | -------- | ------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person.py) | caffe | person | [R-50-FPN-Caffe-3x](./faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | 3.7 | 55.8 | [config](./faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person/faster_rcnn_r50_fpn_1x_coco-person_20201216_175929-d022e227.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person/faster_rcnn_r50_fpn_1x_coco-person_20201216_175929.log.json) |
| [R-50-FPN](./faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person-bicycle-car.py) | caffe | person-bicycle-car | [R-50-FPN-Caffe-3x](./faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | 3.7 | 44.1 | [config](./faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person-bicycle-car.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car_20201216_173117-6eda6d92.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car/faster_rcnn_r50_fpn_1x_coco-person-bicycle-car_20201216_173117.log.json) |
PyTorch/NLP/Conformer-main/mmdetection/configs/faster_rcnn/faster_rcnn_conformer_small_patch32_fpn_1x_coco.py 0 → 100644
View file @ a4372e17
_base_ = [
'../_base_/default_runtime.py'
]
model = dict(
type='FasterRCNN',
pretrained=None,
backbone=dict(
type='Conformer',
embed_dim=384,
depth=12,
patch_size=32,
channel_ratio=4,
num_heads=6,
mlp_ratio=4,
qkv_bias=True,
norm_eval=True,
frozen_stages=1
),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 1024],
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_across_levels=False,
nms_pre=2000,
nms_post=1000,
max_num=1000,
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,
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_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_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)
))
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=(1344, 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=(1344, 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')
# optimizer
optimizer = dict(
type='AdamW',
lr=0.0001,
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])
total_epochs = 12
# optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
find_unused_parameters=True
\ No newline at end of file
PyTorch/NLP/Conformer-main/mmdetection/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py 0 → 100644
View file @ a4372e17
_base_ = [
'../_base_/models/faster_rcnn_r50_fpn.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
PyTorch/NLP/Conformer-main/mmdetection/configs/mask_rcnn/README.md 0 → 100644
View file @ a4372e17
# Mask R-CNN
## Introduction
[ALGORITHM]
```latex
@article{He_2017,
title={Mask R-CNN},
journal={2017 IEEE International Conference on Computer Vision (ICCV)},
publisher={IEEE},
author={He, Kaiming and Gkioxari, Georgia and Dollar, Piotr and Girshick, Ross},
year={2017},
month={Oct}
}
```
## Results and models
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: |
| R-50-FPN | caffe | 1x | 4.3 | | 38.0 | 34.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_1x_coco/mask_rcnn_r50_caffe_fpn_1x_coco_bbox_mAP-0.38__segm_mAP-0.344_20200504_231812-0ebd1859.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_1x_coco/mask_rcnn_r50_caffe_fpn_1x_coco_20200504_231812.log.json) |
| R-50-FPN | pytorch | 1x | 4.4 | 16.1 | 38.2 | 34.7 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205_050542.log.json) |
| R-50-FPN | pytorch | 2x | - | - | 39.2 | 35.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_2x_coco/mask_rcnn_r50_fpn_2x_coco_bbox_mAP-0.392__segm_mAP-0.354_20200505_003907-3e542a40.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_2x_coco/mask_rcnn_r50_fpn_2x_coco_20200505_003907.log.json) |
| R-101-FPN | caffe | 1x | | | 40.4 | 36.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r101_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_caffe_fpn_1x_coco/mask_rcnn_r101_caffe_fpn_1x_coco_20200601_095758-805e06c1.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_caffe_fpn_1x_coco/mask_rcnn_r101_caffe_fpn_1x_coco_20200601_095758.log.json)|
| R-101-FPN | pytorch | 1x | 6.4 | 13.5 | 40.0 | 36.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_fpn_1x_coco/mask_rcnn_r101_fpn_1x_coco_20200204-1efe0ed5.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_fpn_1x_coco/mask_rcnn_r101_fpn_1x_coco_20200204_144809.log.json) |
| R-101-FPN | pytorch | 2x | - | - | 40.8 | 36.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r101_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_fpn_2x_coco/mask_rcnn_r101_fpn_2x_coco_bbox_mAP-0.408__segm_mAP-0.366_20200505_071027-14b391c7.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_fpn_2x_coco/mask_rcnn_r101_fpn_2x_coco_20200505_071027.log.json) |
| X-101-32x4d-FPN | pytorch | 1x | 7.6 | 11.3 | 41.9 | 37.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco/mask_rcnn_x101_32x4d_fpn_1x_coco_20200205-478d0b67.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco/mask_rcnn_x101_32x4d_fpn_1x_coco_20200205_034906.log.json) |
| X-101-32x4d-FPN | pytorch | 2x | - | - | 42.2 | 37.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_x101_32x4d_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_32x4d_fpn_2x_coco/mask_rcnn_x101_32x4d_fpn_2x_coco_bbox_mAP-0.422__segm_mAP-0.378_20200506_004702-faef898c.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_32x4d_fpn_2x_coco/mask_rcnn_x101_32x4d_fpn_2x_coco_20200506_004702.log.json) |
| X-101-64x4d-FPN | pytorch | 1x | 10.7 | 8.0 | 42.8 | 38.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_x101_64x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_64x4d_fpn_1x_coco/mask_rcnn_x101_64x4d_fpn_1x_coco_20200201-9352eb0d.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_64x4d_fpn_1x_coco/mask_rcnn_x101_64x4d_fpn_1x_coco_20200201_124310.log.json) |
| X-101-64x4d-FPN | pytorch | 2x | - | - | 42.7 | 38.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_x101_64x4d_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_64x4d_fpn_2x_coco/mask_rcnn_x101_64x4d_fpn_2x_coco_20200509_224208-39d6f70c.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_64x4d_fpn_2x_coco/mask_rcnn_x101_64x4d_fpn_2x_coco_20200509_224208.log.json)|
| X-101-32x8d-FPN | pytorch | 1x | - | - | 42.8 | 38.3 | |
## Pre-trained Models
We also train some models with longer schedules and multi-scale training. The users could finetune them for downstream tasks.
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: |
| [R-50-FPN](./mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco.py) | caffe | 2x | 4.3 | | 40.3 | 36.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco_bbox_mAP-0.403__segm_mAP-0.365_20200504_231822-a75c98ce.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco_20200504_231822.log.json)
| [R-50-FPN](./mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco.py) | caffe | 3x | 4.3 | | 40.8 | 37.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_20200504_163245.log.json)
| [X-101-32x8d-FPN](./mask_rcnn_x101_32x8d_fpn_mstrain-poly_3x_coco.py) | pytorch | 1x | - | | 43.6 | 39.0 |
| [X-101-32x8d-FPN](./mask_rcnn_x101_32x8d_fpn_mstrain-poly_3x_coco.py) | pytorch | 3x | - | | 44.0 | 39.3 |
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