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

添加openmmlab测试用例

parent b21b0c01
_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='1111',
kv_stride=2),
stages=(False, False, True, True),
position='after_conv2')
]))
_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='1111',
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)))
Collections:
- Name: Empirical Attention
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- Deformable Convolution
- FPN
- RPN
- ResNet
- RoIAlign
- Spatial Attention
Paper: https://arxiv.org/pdf/1904.05873
README: configs/empirical_attention/README.md
Models:
- Name: faster_rcnn_r50_fpn_attention_1111_1x_coco
In Collection: Empirical Attention
Config: configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x_coco.py
Metadata:
Training Memory (GB): 8.0
inference time (s/im): 0.07246
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.0
Weights: 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
- Name: faster_rcnn_r50_fpn_attention_0010_1x_coco
In Collection: Empirical Attention
Config: configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x_coco.py
Metadata:
Training Memory (GB): 4.2
inference time (s/im): 0.05435
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 39.1
Weights: 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
- Name: faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco
In Collection: Empirical Attention
Config: configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco.py
Metadata:
Training Memory (GB): 8.0
inference time (s/im): 0.07874
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 42.1
Weights: 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
- Name: faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco
In Collection: Empirical Attention
Config: configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco.py
Metadata:
Training Memory (GB): 4.2
inference time (s/im): 0.05848
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 42.0
Weights: 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
# Fast R-CNN
## Introduction
<!-- [ALGORITHM] -->
```latex
@inproceedings{girshick2015fast,
title={Fast r-cnn},
author={Girshick, Ross},
booktitle={Proceedings of the IEEE international conference on computer vision},
year={2015}
}
```
## Results and models
_base_ = './fast_rcnn_r50_caffe_fpn_1x_coco.py'
model = dict(
pretrained='open-mmlab://detectron2/resnet101_caffe',
backbone=dict(depth=101))
_base_ = './fast_rcnn_r50_fpn_1x_coco.py'
model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))
_base_ = './fast_rcnn_r50_fpn_2x_coco.py'
model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))
_base_ = './fast_rcnn_r50_fpn_1x_coco.py'
model = dict(
pretrained='open-mmlab://detectron2/resnet50_caffe',
backbone=dict(
norm_cfg=dict(type='BN', requires_grad=False), style='caffe'))
# use caffe img_norm
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadProposals', num_max_proposals=2000),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadProposals', num_max_proposals=None),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['proposals']),
dict(
type='ToDataContainer',
fields=[dict(key='proposals', stack=False)]),
dict(type='Collect', keys=['img', 'proposals']),
])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
_base_ = [
'../_base_/models/fast_rcnn_r50_fpn.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
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='LoadProposals', num_max_proposals=2000),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadProposals', num_max_proposals=None),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['proposals']),
dict(
type='ToDataContainer',
fields=[dict(key='proposals', stack=False)]),
dict(type='Collect', keys=['img', 'proposals']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_train2017.pkl',
pipeline=train_pipeline),
val=dict(
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
pipeline=test_pipeline),
test=dict(
proposal_file=data_root + 'proposals/rpn_r50_fpn_1x_val2017.pkl',
pipeline=test_pipeline))
_base_ = './fast_rcnn_r50_fpn_1x_coco.py'
# learning policy
lr_config = dict(step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=24)
# 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) &#124; [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](https://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) &#124; [log](https://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](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth) &#124; [log](https://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](https://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) &#124; [log](https://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](https://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) &#124; [log](https://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](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_1x_coco/faster_rcnn_r101_fpn_1x_coco_20200130-f513f705.pth) &#124; [log](https://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](https://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) &#124; [log](https://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](https://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) &#124; [log](https://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](https://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) &#124; [log](https://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](https://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) &#124; [log](https://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](https://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) &#124; [log](https://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](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth) &#124; [log](https://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](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_iou_1x_coco-fdd207f3.pth) &#124; [log](https://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](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_giou_1x_coco-0eada910.pth) &#124; [log](https://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](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco-98ad993b.pth) &#124; [log](https://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) &#124; [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) &#124; [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 | 3.7 | | 39.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py) | [model](https://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) &#124; [log](https://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 | 3.7 | | 39.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_20210526_095054-f002305e.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_20210526_095054.log.json) |
| [R-50-FPN](./faster_rcnn_r50_fpn_mstrain_3x_coco.py) | pytorch | 3x | 3.9 | | 40.3 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_mstrain_3x_coco/faster_rcnn_r50_fpn_mstrain_3x_coco_20210524_110822-3a066a07.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_20210524_110822.log.json) |
| [R-101-FPN](./faster_rcnn_r101_caffe_fpn_mstrain_3x_coco.py) | caffe | 3x | 5.6 | | 42.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r101_caffe_fpn_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_caffe_fpn_mstrain_3x_coco/faster_rcnn_r101_caffe_fpn_mstrain_3x_coco_20210526_095742-9178be4b.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_caffe_fpn_mstrain_3x_coco/faster_rcnn_r101_caffe_fpn_mstrain_3x_coco_20210526_095742.log.json) |
| [R-101-FPN](./faster_rcnn_r101_fpn_mstrain_3x_coco.py) | pytorch | 3x | 5.8 | | 41.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r101_fpn_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_mstrain_3x_coco/faster_rcnn_r101_fpn_mstrain_3x_coco_20210524_110822-78060bff.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_mstrain_3x_coco/faster_rcnn_r101_fpn_mstrain_3x_coco_20210524_110822.log.json) |
| [X-101-32x4d-FPN](./faster_rcnn_x101_32x4d_fpn_mstrain_3x_coco.py) | pytorch | 3x | 7.0 | | 42.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_32x4d_fpn_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x4d_fpn_mstrain_3x_coco/faster_rcnn_x101_32x4d_fpn_mstrain_3x_coco_20210524_124151-e8595dde.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x4d_fpn_mstrain_3x_coco/faster_rcnn_x101_32x4d_fpn_mstrain_3x_coco_20210524_124151.log.json) |
| [X-101-32x8d-FPN](./faster_rcnn_x101_32x8d_fpn_mstrain_3x_coco.py) | pytorch | 3x | 10.1 | | 42.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_32x8d_fpn_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x8d_fpn_mstrain_3x_coco/faster_rcnn_x101_32x8d_fpn_mstrain_3x_coco_20210604_182954-002e082a.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_32x8d_fpn_mstrain_3x_coco/faster_rcnn_x101_32x8d_fpn_mstrain_3x_coco_20210604_182954.log.json) |
| [X-101-64x4d-FPN](./faster_rcnn_x101_64x4d_fpn_mstrain_3x_coco.py) | pytorch | 3x | 10.0 | | 43.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_64x4d_fpn_mstrain_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_mstrain_3x_coco/faster_rcnn_x101_64x4d_fpn_mstrain_3x_coco_20210524_124528-26c63de6.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_mstrain_3x_coco/faster_rcnn_x101_64x4d_fpn_mstrain_3x_coco_20210524_124528.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) &#124; [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) &#124; [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) |
_base_ = './faster_rcnn_r50_caffe_fpn_1x_coco.py'
model = dict(
pretrained='open-mmlab://detectron2/resnet101_caffe',
backbone=dict(depth=101))
_base_ = 'faster_rcnn_r50_fpn_mstrain_3x_coco.py'
model = dict(
pretrained='open-mmlab://detectron2/resnet101_caffe',
backbone=dict(
depth=101,
norm_cfg=dict(requires_grad=False),
norm_eval=True,
style='caffe'))
# use caffe img_norm
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=[(1333, 640), (1333, 800)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
train=dict(dataset=dict(pipeline=train_pipeline)),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
_base_ = './faster_rcnn_r50_fpn_1x_coco.py'
model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))
_base_ = './faster_rcnn_r50_fpn_2x_coco.py'
model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))
_base_ = 'faster_rcnn_r50_fpn_mstrain_3x_coco.py'
model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))
_base_ = [
'../_base_/models/faster_rcnn_r50_caffe_c4.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
# use caffe img_norm
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
_base_ = [
'../_base_/models/faster_rcnn_r50_caffe_dc5.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
# use caffe img_norm
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
_base_ = [
'../_base_/models/faster_rcnn_r50_caffe_dc5.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
# use caffe img_norm
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
(1333, 768), (1333, 800)],
multiscale_mode='value',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
_base_ = './faster_rcnn_r50_caffe_dc5_mstrain_1x_coco.py'
# learning policy
lr_config = dict(step=[28, 34])
runner = dict(type='EpochBasedRunner', max_epochs=36)
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