H-Deformable-DETR for MMDet

This is the official implementation of the paper "DETRs with Hybrid Matching".

Authors: Ding Jia, Yuhui Yuan, Haodi He, Xiaopei Wu, Haojun Yu, Weihong Lin, Lei Sun, Chao Zhang, Han Hu

Model ZOO

🍺🍺🍺Please checkout the branch mmdetection-with-plug-in for more clean orgnizations.📣📣📣

We provide a set of baseline results and trained models available for download:

Models with the ResNet-50 backbone

Notice that to align with the offical implement of Deformable DETR and other backbones, we do not freeze the stage 1-th in the ResNet-50 backbone.

Models with Swin Transformer backbones

Installation

We test our models under python=3.7.10,pytorch=1.10.1,cuda=10.2. Other versions might be available as well.

1. Clone this repo sh git https://github.com/HDETR/H-Deformable-DETR-mmdet.git cd H-Deformable-DETR-mmdet

2. Install Pytorch and torchvision

Follow the instruction on https://pytorch.org/get-started/locally/. ```sh

an example:

conda install -c pytorch pytorch torchvision ```

1. Install other needed packages sh pip install -r requirements.txt pip install openmim mim install mmcv-full pip install -e .

Data

Please download COCO 2017 dataset and organize them as following: H-Deformable-DETR-mmdet ├── data │ ├── coco │ │ ├── train2017 │ │ ├── val2017 │ │ └── annotations | | ├── instances_train2017.json | | └── instances_val2017.json

Run

To train a model using 8 cards

Bash GPUS_PER_NODE=8 ./tools/dist_train.sh \ <config path> \ 8

To train/eval a model with the swin transformer backbone, you need to download the backbone from the offical repo frist and specify argumentcheckpoint like our config.

To eval a model using 8 cards

Bash GPUS_PER_NODE=8 tools/dist_test.sh \ <config path> \ <checkpoint path> \ 8 --eval bbox

Modified files compared to original MMDet

• configs/deformable_detr: add baseline configs
• configs/h-deformable-detr: add h-deformable-detr configs
• mmdet/models/utils/transformer.py: enable tricks and decoderselfattn_mask
• mmdet/models/denseheads/hybridbranchdeformabledetr_head.py: enable hybrid branch strategy and tricks
• mmdet/models/denseheads/deformabledetr_head.py: enable tricks

Citing H-Deformable-DETR for MMDet

If you find H-Deformable-DETR for MMDet useful in your research, please consider citing: ```bibtex @article{jia2022detrs, title={DETRs with Hybrid Matching}, author={Jia, Ding and Yuan, Yuhui and He, Haodi and Wu, Xiaopei and Yu, Haojun and Lin, Weihong and Sun, Lei and Zhang, Chao and Hu, Han}, journal={arXiv preprint arXiv:2207.13080}, year={2022} }

@article{zhu2020deformable, title={Deformable detr: Deformable transformers for end-to-end object detection}, author={Zhu, Xizhou and Su, Weijie and Lu, Lewei and Li, Bin and Wang, Xiaogang and Dai, Jifeng}, journal={arXiv preprint arXiv:2010.04159}, year={2020} } ```