Home

Awesome

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

License: MIT

Paper (CVPR 2021)

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

Updates

Models

Methodinf_timetrain_timebox APdownload
R50_100pro_3x23 FPS19h42.8model | log
R50_300pro_3x22 FPS24h45.0model | log
R101_100pro_3x19 FPS25h44.1model | log
R101_300pro_3x18 FPS29h46.4model | log

If download link is invalid, models and logs are also available in Github Release and Baidu Drive by code wt9n.

Notes

Methodinf_timetrain_timebox APcodebase
R50_300pro_3x22 FPS24h45.0detectron2
R50_300pro_3x.detco22 FPS28h46.5detectron2
PVTSmall_300pro_3x13 FPS50h45.7mmdetection
PVTv2-b2_300pro_3x11 FPS76h50.1mmdetection

Installation

The codebases are built on top of Detectron2 and DETR.

Requirements

Steps

  1. Install and build libs
git clone https://github.com/PeizeSun/SparseR-CNN.git
cd SparseR-CNN
python setup.py build develop
  1. Link coco dataset path to SparseR-CNN/datasets/coco
mkdir -p datasets/coco
ln -s /path_to_coco_dataset/annotations datasets/coco/annotations
ln -s /path_to_coco_dataset/train2017 datasets/coco/train2017
ln -s /path_to_coco_dataset/val2017 datasets/coco/val2017
  1. Train SparseR-CNN
python projects/SparseRCNN/train_net.py --num-gpus 8 \
    --config-file projects/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml
  1. Evaluate SparseR-CNN
python projects/SparseRCNN/train_net.py --num-gpus 8 \
    --config-file projects/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml \
    --eval-only MODEL.WEIGHTS path/to/model.pth
  1. Visualize SparseR-CNN
python demo/demo.py\
    --config-file projects/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml \
    --input path/to/images --output path/to/save_images --confidence-threshold 0.4 \
    --opts MODEL.WEIGHTS path/to/model.pth

Third-party resources

License

SparseR-CNN is released under MIT License.

Citing

If you use SparseR-CNN in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:


@article{peize2020sparse,
  title   =  {{SparseR-CNN}: End-to-End Object Detection with Learnable Proposals},
  author  =  {Peize Sun and Rufeng Zhang and Yi Jiang and Tao Kong and Chenfeng Xu and Wei Zhan and Masayoshi Tomizuka and Lei Li and Zehuan Yuan and Changhu Wang and Ping Luo},
  journal =  {arXiv preprint arXiv:2011.12450},
  year    =  {2020}
}