H-Deformable-DETR

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

News

2022.09.14 We support H-Deformable-DETR w/ ViT-L (MAE) achieves 56.6 AP on COCO val with 4-scale feature maps without using LSJ (large scale jittering) adopted by the original ViT-Det.

Model ZOO

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

Models with ViT (MAE) backbone

Name	Backbone	query	LSJ	encoder	epochs	AP	download
H-Deformable-DETR + tricks	ViT-B	300	❌	6	12	50.6	model
H-Deformable-DETR + tricks	ViT-B	300	❌	2	12	49.8	model
H-Deformable-DETR + tricks	ViT-B	300	❌	0	12	47.1	model
H-Deformable-DETR + tricks	ViT-L	300	❌	6	12	51.1	model
H-Deformable-DETR + tricks	ViT-L	300	❌	6	36	55.5	model
H-Deformable-DETR + tricks	ViT-L	300	❌	6	75	56.5	model
H-Deformable-DETR + tricks	ViT-L	300	❌	6	100	56.6	model

Installation

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

Clone this repo

git https://github.com/HDETR/H-Deformable-DETR.git
cd H-Deformable-DETR

Install Pytorch and torchvision

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

# an example:
conda install -c pytorch pytorch torchvision

Install other needed packages

pip install -r requirements.txt
pip install openmim
mim install mmcv-full
pip install mmdet

Compiling CUDA operators

cd models/ops
python setup.py build install
# unit test (should see all checking is True)
python test.py
cd ../..

Data

Please download COCO 2017 dataset and organize them as following:

coco_path/
  ├── train2017/
  ├── val2017/
  └── annotations/
  	├── instances_train2017.json
  	└── instances_val2017.json

Run

To train a model using 8 cards

GPUS_PER_NODE=8 ./tools/run_dist_launch.sh 8 <config path> \
    --coco_path <coco path>

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

To eval a model using 8 cards

GPUS_PER_NODE=8 ./tools/run_dist_launch.sh 8 <config path> \
    --coco_path <coco path> --eval --resume <checkpoint path>

Distributed Run

You can refer to Deformable-DETR to enable training on multiple nodes.

Modified files compared to vanilla Deformable DETR

To support swin backbones

models/backbone.py
models/swin_transformer.py
mmcv_custom

To support eval in the training set

datasets/coco.py
datasets/__init__.py

To support Hybrid-branch, tricks and checkpoint

main.py
engine.py
models/deformable_detr.py
models/deformable_transformer.py

To support fp16

models/ops/modules/ms_deform_attn.py
models/ops/functions/ms_deform_attn_func.py

To fix a pytorch version bug

util/misc.py

Addictional packages needed

wandb: for logging
mmdet: for swin backbones
mmcv: for swin backbones
timm: for swin backbones

Citing H-Deformable-DETR

If you find H-Deformable-DETR useful in your research, please consider citing:

@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}
}

kxqt/H-Deformable-DETR