Skip to content

GitLab

Commit 85529f35 authored by unknown's avatar unknown
Browse files

添加openmmlab测试用例

parent b21b0c01
Show whitespace changes
Inline Side-by-side
Showing with 679 additions and 0 deletions
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/cascade_rcnn_r50_rfp_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/cascade_rcnn_r50_fpn.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
backbone=dict(
type='DetectoRS_ResNet',
conv_cfg=dict(type='ConvAWS'),
output_img=True),
neck=dict(
type='RFP',
rfp_steps=2,
aspp_out_channels=64,
aspp_dilations=(1, 3, 6, 1),
rfp_backbone=dict(
rfp_inplanes=256,
type='DetectoRS_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,
conv_cfg=dict(type='ConvAWS'),
pretrained='torchvision://resnet50',
style='pytorch')))
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/cascade_rcnn_r50_sac_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/cascade_rcnn_r50_fpn.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
backbone=dict(
type='DetectoRS_ResNet',
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True)))
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/detectors_cascade_rcnn_r50_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/cascade_rcnn_r50_fpn.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
backbone=dict(
type='DetectoRS_ResNet',
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True),
output_img=True),
neck=dict(
type='RFP',
rfp_steps=2,
aspp_out_channels=64,
aspp_dilations=(1, 3, 6, 1),
rfp_backbone=dict(
rfp_inplanes=256,
type='DetectoRS_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,
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True),
pretrained='torchvision://resnet50',
style='pytorch')))
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/detectors_htc_r101_20e_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../htc/htc_r101_fpn_20e_coco.py'
model = dict(
backbone=dict(
type='DetectoRS_ResNet',
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True),
output_img=True),
neck=dict(
type='RFP',
rfp_steps=2,
aspp_out_channels=64,
aspp_dilations=(1, 3, 6, 1),
rfp_backbone=dict(
rfp_inplanes=256,
type='DetectoRS_ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True),
pretrained='torchvision://resnet101',
style='pytorch')))
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/detectors_htc_r50_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../htc/htc_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
type='DetectoRS_ResNet',
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True),
output_img=True),
neck=dict(
type='RFP',
rfp_steps=2,
aspp_out_channels=64,
aspp_dilations=(1, 3, 6, 1),
rfp_backbone=dict(
rfp_inplanes=256,
type='DetectoRS_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,
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True),
pretrained='torchvision://resnet50',
style='pytorch')))
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/htc_r50_rfp_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../htc/htc_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
type='DetectoRS_ResNet',
conv_cfg=dict(type='ConvAWS'),
output_img=True),
neck=dict(
type='RFP',
rfp_steps=2,
aspp_out_channels=64,
aspp_dilations=(1, 3, 6, 1),
rfp_backbone=dict(
rfp_inplanes=256,
type='DetectoRS_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,
conv_cfg=dict(type='ConvAWS'),
pretrained='torchvision://resnet50',
style='pytorch')))
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/htc_r50_sac_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../htc/htc_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
type='DetectoRS_ResNet',
conv_cfg=dict(type='ConvAWS'),
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True)))
openmmlab_test/mmdetection-speed_xinpian/configs/detectors/metafile.yml 0 → 100644
View file @ 85529f35
Collections:
- Name: DetectoRS
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- ASPP
- FPN
- RFP
- RPN
- ResNet
- RoIAlign
- SAC
Paper: https://arxiv.org/abs/2006.02334
README: configs/detectors/README.md
Models:
- Name: cascade_rcnn_r50_rfp_1x_coco
In Collection: DetectoRS
Config: configs/detectors/cascade_rcnn_r50_rfp_1x_coco.py
Metadata:
Training Memory (GB): 7.5
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 44.8
Weights: https://download.openmmlab.com/mmdetection/v2.0/detectors/cascade_rcnn_r50_rfp_1x_coco/cascade_rcnn_r50_rfp_1x_coco-8cf51bfd.pth
- Name: cascade_rcnn_r50_sac_1x_coco
In Collection: DetectoRS
Config: configs/detectors/cascade_rcnn_r50_sac_1x_coco.py
Metadata:
Training Memory (GB): 5.6
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 45.0
Weights: https://download.openmmlab.com/mmdetection/v2.0/detectors/cascade_rcnn_r50_sac_1x_coco/cascade_rcnn_r50_sac_1x_coco-24bfda62.pth
- Name: detectors_cascade_rcnn_r50_1x_coco
In Collection: DetectoRS
Config: configs/detectors/detectors_cascade_rcnn_r50_1x_coco.py
Metadata:
Training Memory (GB): 9.9
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 47.4
Weights: https://download.openmmlab.com/mmdetection/v2.0/detectors/detectors_cascade_rcnn_r50_1x_coco/detectors_cascade_rcnn_r50_1x_coco-32a10ba0.pth
- Name: htc_r50_rfp_1x_coco
In Collection: DetectoRS
Config: configs/detectors/htc_r50_rfp_1x_coco.py
Metadata:
Training Memory (GB): 11.2
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 46.6
- Task: Instance Segmentation
Dataset: COCO
Metrics:
mask AP: 40.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/detectors/htc_r50_rfp_1x_coco/htc_r50_rfp_1x_coco-8ff87c51.pth
- Name: htc_r50_sac_1x_coco
In Collection: DetectoRS
Config: configs/detectors/htc_r50_sac_1x_coco.py
Metadata:
Training Memory (GB): 9.3
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 46.4
- Task: Instance Segmentation
Dataset: COCO
Metrics:
mask AP: 40.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/detectors/htc_r50_sac_1x_coco/htc_r50_sac_1x_coco-bfa60c54.pth
- Name: detectors_htc_r50_1x_coco
In Collection: DetectoRS
Config: configs/detectors/detectors_htc_r50_1x_coco.py
Metadata:
Training Memory (GB): 13.6
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 49.1
- Task: Instance Segmentation
Dataset: COCO
Metrics:
mask AP: 42.6
Weights: https://download.openmmlab.com/mmdetection/v2.0/detectors/detectors_htc_r50_1x_coco/detectors_htc_r50_1x_coco-329b1453.pth
openmmlab_test/mmdetection-speed_xinpian/configs/detr/README.md 0 → 100644
View file @ 85529f35
# DETR
## Introduction
<!-- [ALGORITHM] -->
We provide the config files for DETR: [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872).
```BibTeX
@inproceedings{detr,
author = {Nicolas Carion and
Francisco Massa and
Gabriel Synnaeve and
Nicolas Usunier and
Alexander Kirillov and
Sergey Zagoruyko},
title = {End-to-End Object Detection with Transformers},
booktitle = {ECCV},
year = {2020}
}
```
## Results and Models
| Backbone | Model | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
|:------:|:--------:|:-------:|:--------:|:--------------:|:------:|:------:|:--------:|
| R-50 | DETR |150e |7.9| | 40.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/detr/detr_r50_8x2_150e_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/detr/detr_r50_8x2_150e_coco/detr_r50_8x2_150e_coco_20201130_194835-2c4b8974.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/detr/detr_r50_8x2_150e_coco/detr_r50_8x2_150e_coco_20201130_194835.log.json) |
openmmlab_test/mmdetection-speed_xinpian/configs/detr/detr_r50_8x2_150e_coco.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/datasets/coco_detection.py', '../_base_/default_runtime.py'
]
model = dict(
type='DETR',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(3, ),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='pytorch'),
bbox_head=dict(
type='DETRHead',
num_classes=80,
in_channels=2048,
transformer=dict(
type='Transformer',
encoder=dict(
type='DetrTransformerEncoder',
num_layers=6,
transformerlayers=dict(
type='BaseTransformerLayer',
attn_cfgs=[
dict(
type='MultiheadAttention',
embed_dims=256,
num_heads=8,
dropout=0.1)
],
feedforward_channels=2048,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
decoder=dict(
type='DetrTransformerDecoder',
return_intermediate=True,
num_layers=6,
transformerlayers=dict(
type='DetrTransformerDecoderLayer',
attn_cfgs=dict(
type='MultiheadAttention',
embed_dims=256,
num_heads=8,
dropout=0.1),
feedforward_channels=2048,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm')),
)),
positional_encoding=dict(
type='SinePositionalEncoding', num_feats=128, normalize=True),
loss_cls=dict(
type='CrossEntropyLoss',
bg_cls_weight=0.1,
use_sigmoid=False,
loss_weight=1.0,
class_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=5.0),
loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
# training and testing settings
train_cfg=dict(
assigner=dict(
type='HungarianAssigner',
cls_cost=dict(type='ClassificationCost', weight=1.),
reg_cost=dict(type='BBoxL1Cost', weight=5.0, box_format='xywh'),
iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
test_cfg=dict(max_per_img=100))
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
# train_pipeline, NOTE the img_scale and the Pad's size_divisor is different
# from the default setting in mmdet.
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[[
dict(
type='Resize',
img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
multiscale_mode='value',
keep_ratio=True)
],
[
dict(
type='Resize',
img_scale=[(400, 1333), (500, 1333), (600, 1333)],
multiscale_mode='value',
keep_ratio=True),
dict(
type='RandomCrop',
crop_type='absolute_range',
crop_size=(384, 600),
allow_negative_crop=True),
dict(
type='Resize',
img_scale=[(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
multiscale_mode='value',
override=True,
keep_ratio=True)
]]),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=1),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
# test_pipeline, NOTE the Pad's size_divisor is different from the default
# setting (size_divisor=32). While there is little effect on the performance
# whether we use the default setting or use size_divisor=1.
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=1),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0001,
paramwise_cfg=dict(
custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)}))
optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=[100])
runner = dict(type='EpochBasedRunner', max_epochs=150)
openmmlab_test/mmdetection-speed_xinpian/configs/detr/metafile.yml 0 → 100644
View file @ 85529f35
Collections:
- Name: DETR
Metadata:
Training Data: COCO
Training Techniques:
- AdamW
- Multi Scale Train
- Gradient Clip
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- ResNet
- Transformer
Paper: https://arxiv.org/abs/2005.12872
README: configs/detr/README.md
Models:
- Name: detr_r50_8x2_150e_coco
In Collection: DETR
Config: configs/detr/detr_r50_8x2_150e_coco.py
Metadata:
Training Memory (GB): 7.9
Epochs: 150
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.1
Weights: https://download.openmmlab.com/mmdetection/v2.0/detr/detr_r50_8x2_150e_coco/detr_r50_8x2_150e_coco_20201130_194835-2c4b8974.pth
openmmlab_test/mmdetection-speed_xinpian/configs/double_heads/README.md 0 → 100644
View file @ 85529f35
# Rethinking Classification and Localization for Object Detection
## Introduction
<!-- [ALGORITHM] -->
```latex
@article{wu2019rethinking,
title={Rethinking Classification and Localization for Object Detection},
author={Yue Wu and Yinpeng Chen and Lu Yuan and Zicheng Liu and Lijuan Wang and Hongzhi Li and Yun Fu},
year={2019},
eprint={1904.06493},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## Results and models
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: |
| R-50-FPN | pytorch | 1x | 6.8 | 9.5 | 40.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/double_heads/dh_faster_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/double_heads/dh_faster_rcnn_r50_fpn_1x_coco/dh_faster_rcnn_r50_fpn_1x_coco_20200130-586b67df.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/double_heads/dh_faster_rcnn_r50_fpn_1x_coco/dh_faster_rcnn_r50_fpn_1x_coco_20200130_220238.log.json) |
openmmlab_test/mmdetection-speed_xinpian/configs/double_heads/dh_faster_rcnn_r50_fpn_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(
roi_head=dict(
type='DoubleHeadRoIHead',
reg_roi_scale_factor=1.3,
bbox_head=dict(
_delete_=True,
type='DoubleConvFCBBoxHead',
num_convs=4,
num_fcs=2,
in_channels=256,
conv_out_channels=1024,
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=2.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=2.0))))
openmmlab_test/mmdetection-speed_xinpian/configs/double_heads/metafile.yml 0 → 100644
View file @ 85529f35
Collections:
- Name: Rethinking Classification and Localization for Object Detection
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- FPN
- RPN
- ResNet
- RoIAlign
Paper: https://arxiv.org/pdf/1904.06493
README: configs/double_heads/README.md
Models:
- Name: dh_faster_rcnn_r50_fpn_1x_coco
In Collection: Rethinking Classification and Localization for Object Detection
Config: configs/double_heads/dh_faster_rcnn_r50_fpn_1x_coco.py
Metadata:
Training Memory (GB): 6.8
inference time (s/im): 0.10526
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.0
Weights: https://download.openmmlab.com/mmdetection/v2.0/double_heads/dh_faster_rcnn_r50_fpn_1x_coco/dh_faster_rcnn_r50_fpn_1x_coco_20200130-586b67df.pth
openmmlab_test/mmdetection-speed_xinpian/configs/dynamic_rcnn/README.md 0 → 100644
View file @ 85529f35
# Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
## Introduction
<!-- [ALGORITHM] -->
```
@article{DynamicRCNN,
author = {Hongkai Zhang and Hong Chang and Bingpeng Ma and Naiyan Wang and Xilin Chen},
title = {Dynamic {R-CNN}: Towards High Quality Object Detection via Dynamic Training},
journal = {arXiv preprint arXiv:2004.06002},
year = {2020}
}
```
## Results and Models
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
|:---------:|:-------:|:-------:|:--------:|:--------------:|:------:|:------:|:--------:|
| R-50 | pytorch | 1x | 3.8 | | 38.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/dynamic_rcnn/dynamic_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/dynamic_rcnn/dynamic_rcnn_r50_fpn_1x/dynamic_rcnn_r50_fpn_1x-62a3f276.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/dynamic_rcnn/dynamic_rcnn_r50_fpn_1x/dynamic_rcnn_r50_fpn_1x_20200618_095048.log.json) |
openmmlab_test/mmdetection-speed_xinpian/configs/dynamic_rcnn/dynamic_rcnn_r50_fpn_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(
roi_head=dict(
type='DynamicRoIHead',
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='SmoothL1Loss', beta=1.0, loss_weight=1.0))),
train_cfg=dict(
rpn_proposal=dict(nms=dict(iou_threshold=0.85)),
rcnn=dict(
dynamic_rcnn=dict(
iou_topk=75,
beta_topk=10,
update_iter_interval=100,
initial_iou=0.4,
initial_beta=1.0))),
test_cfg=dict(rpn=dict(nms=dict(iou_threshold=0.85))))
openmmlab_test/mmdetection-speed_xinpian/configs/dynamic_rcnn/metafile.yml 0 → 100644
View file @ 85529f35
Collections:
- Name: Dynamic R-CNN
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- Dynamic R-CNN
- FPN
- RPN
- ResNet
- RoIAlign
Paper: https://arxiv.org/pdf/2004.06002
README: configs/dynamic_rcnn/README.md
Models:
- Name: dynamic_rcnn_r50_fpn_1x_coco
In Collection: Dynamic R-CNN
Config: configs/dynamic_rcnn/dynamic_rcnn_r50_fpn_1x_coco.py
Metadata:
Training Memory (GB): 3.8
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 38.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/dynamic_rcnn/dynamic_rcnn_r50_fpn_1x/dynamic_rcnn_r50_fpn_1x-62a3f276.pth
openmmlab_test/mmdetection-speed_xinpian/configs/empirical_attention/README.md 0 → 100644
View file @ 85529f35
# An Empirical Study of Spatial Attention Mechanisms in Deep Networks
## Introduction
<!-- [ALGORITHM] -->
```latex
@article{zhu2019empirical,
title={An Empirical Study of Spatial Attention Mechanisms in Deep Networks},
author={Zhu, Xizhou and Cheng, Dazhi and Zhang, Zheng and Lin, Stephen and Dai, Jifeng},
journal={arXiv preprint arXiv:1904.05873},
year={2019}
}
```
## Results and Models
| Backbone | Attention Component | DCN | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
|:---------:|:-------------------:|:----:|:-------:|:--------:|:--------------:|:------:|:------:|:--------:|
| R-50 | 1111 | N | 1x | 8.0 | 13.8 | 40.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x_coco/faster_rcnn_r50_fpn_attention_1111_1x_coco_20200130-403cccba.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x_coco/faster_rcnn_r50_fpn_attention_1111_1x_coco_20200130_210344.log.json) |
| R-50 | 0010 | N | 1x | 4.2 | 18.4 | 39.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x_coco/faster_rcnn_r50_fpn_attention_0010_1x_coco_20200130-7cb0c14d.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x_coco/faster_rcnn_r50_fpn_attention_0010_1x_coco_20200130_210125.log.json) |
| R-50 | 1111 | Y | 1x | 8.0 | 12.7 | 42.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco/faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco_20200130-8b2523a6.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco/faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco_20200130_204442.log.json) |
| R-50 | 0010 | Y | 1x | 4.2 | 17.1 | 42.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco_20200130-1a2e831d.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco_20200130_210410.log.json) |
openmmlab_test/mmdetection-speed_xinpian/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(plugins=[
dict(
cfg=dict(
type='GeneralizedAttention',
spatial_range=-1,
num_heads=8,
attention_type='0010',
kv_stride=2),
stages=(False, False, True, True),
position='after_conv2')
]))
openmmlab_test/mmdetection-speed_xinpian/configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco.py 0 → 100644
View file @ 85529f35
_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(
backbone=dict(
plugins=[
dict(
cfg=dict(
type='GeneralizedAttention',
spatial_range=-1,
num_heads=8,
attention_type='0010',
kv_stride=2),
stages=(False, False, True, True),
position='after_conv2')
],
dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)))
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