This is the official repository with PyTorch implementation of LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection.

☀️ If you find this work useful for your research, please kindly star our repo and cite our paper! ☀️

• Release a series of real-time detection models in LW-DETR, including LW-DETR-tiny, LW-DETR-small, LW-DETR-medium, LW-DETR-large and LW-DETR-xlarge, named <LWDETR_*size_60e_coco.pth>. Please refer to Hugging Face to download.
• Release a series of pretrained models in LW-DETR. Please refer to Hugging Face to download.

• 1. Introduction
• 2. Installation
• 3. Preparation
• 4. Train
• 5. Eval
• 6. Deploy
• 7. Main Results
• 8. References
• 9. Citation

LW-DETR is a light-weight detection tranformer, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. LW-DETR leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. LW-DETR improves the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduces window-major feature map organization for improving the efficiency of interleaved attention computation. LW-DETR achieves superior performance than on existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets.

The code is developed and validated under python=3.8.19, pytorch=1.13.0, cuda=11.6,TensorRT-8.6.1.6. Higher versions might be available as well.

1. Create your own Python environment with Anaconda.

conda create -n lwdetr python=3.8.19
conda activate lwdetr

2. Clone this repo.

git clone https://github.com/Atten4Vis/LW-DETR.git
cd LW-DETR

3. Install PyTorch and torchvision.

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

# an example:
conda install pytorch==1.13.0 torchvision==0.14.0 pytorch-cuda=11.6 -c pytorch -c nvidia

4. Install required packages.

For training and evaluation:

pip install -r requirements.txt

For deployment:

Please refer to NVIDIA for installation instruction of TensorRT

pip install -r deploy/requirements.txt

5. Compiling CUDA operators

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

For MS COCO dataset, please download and extract COCO 2017 train and val images with annotations from http://cocodataset.org. We expect the directory structure to be the following:

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

For Objects365 dataset for pretraining, please download Objects365 images with annotations from https://www.objects365.org/overview.html.

All the checkpoints can be found in Hugging Face.

1. Pretraining on Objects365.

• Pretrained the ViT.

We pretrain the ViT on the dataset Objects365 using a MIM method, CAE v2, based on the pretrained models. Please refer to the following link to download the pretrained models, and put them into pretrain_weights/.

• Pretrained LW-DETR.

We retrain the encoder and train the projector and the decoder on Objects365 in a supervision manner. Please refer to the following link to download the pretrained models, and put them into pretrain_weights/.

2. Finetuning on COCO. We finetune the pretrained model on COCO. If you want to reimplement our repo, please skip this step. If you want to directly evaluate our trained models, please refer to the following link to download the finetuned models, and put them into output/.

You can directly run scripts/lwdetr_<model_size>_coco_train.sh file for the training process on coco dataset.

sh scripts/lwdetr_tiny_coco_train.sh /path/to/your/COCODIR

sh scripts/lwdetr_small_coco_train.sh /path/to/your/COCODIR

sh scripts/lwdetr_medium_coco_train.sh /path/to/your/COCODIR

sh scripts/lwdetr_large_coco_train.sh /path/to/your/COCODIR

sh scripts/lwdetr_xlarge_coco_train.sh /path/to/your/COCODIR

You can directly run scripts/lwdetr_<model_size>_coco_eval.sh file for the evaluation process on coco dataset. Please refer to 3. Preparation to download a series of LW-DETR models.

sh scripts/lwdetr_tiny_coco_eval.sh /path/to/your/COCODIR /path/to/your/checkpoint

sh scripts/lwdetr_small_coco_eval.sh /path/to/your/COCODIR /path/to/your/checkpoint

sh scripts/lwdetr_medium_coco_eval.sh /path/to/your/COCODIR /path/to/your/checkpoint

sh scripts/lwdetr_large_coco_eval.sh /path/to/your/COCODIR /path/to/your/checkpoint

sh scripts/lwdetr_xlarge_coco_eval.sh /path/to/your/COCODIR /path/to/your/checkpoint

You can run scripts/lwdetr_<model_size>_coco_export.sh file to export models for development. Before execution, please ensure that TensorRT and cuDNN environment variables are correctly set.

# export ONNX model
sh scripts/lwdetr_tiny_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint
# convert model from ONNX to TensorRT engine as well
sh scripts/lwdetr_tiny_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint --trt

# export ONNX model
sh scripts/lwdetr_small_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint
# convert model from ONNX to TensorRT engine as well
sh scripts/lwdetr_small_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint --trt

# export ONNX model
sh scripts/lwdetr_medium_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint
# convert model from ONNX to TensorRT engine as well
sh scripts/lwdetr_medium_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint --trt

# export ONNX model
sh scripts/lwdetr_large_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint
# convert model from ONNX to TensorRT engine as well
sh scripts/lwdetr_large_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint --trt

# export ONNX model
sh scripts/lwdetr_xlarge_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint
# convert model from ONNX to TensorRT engine as well
sh scripts/lwdetr_xlarge_coco_export.sh /path/to/your/COCODIR /path/to/your/checkpoint --trt

You can use deploy/benchmark.py tool to run benchmarks of inference latency.

# evaluate and benchmark the latency on a onnx model
python deploy/benchmark.py --path=/path/to/your/onnxmodel --coco_path=/path/to/your/COCODIR --run_benchmark 
# evaluate and benchmark the latency on a TensorRT engine
python deploy/benchmark.py --path=/path/to/your/trtengine --coco_path=/path/to/your/COCODIR --run_benchmark 

The main results on coco dataset. We report the mAP as reported in the original paper, as well as the mAP obtained from re-implementation.

Our project is conducted based on the following public paper with code:

• Group DETR
• ViTDet
• Deformable DETR
• Conditional DETR
• YOLOv8
• AlignDETR
• CAE v2
• CAE

If you find this code useful in your research, please kindly consider citing our paper:

    @article{chen2024lw,
        title={LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection},
        author={Chen, Qiang and Su, Xiangbo and Zhang, Xinyu and Wang, Jian and Chen, Jiahui and Shen, Yunpeng and Han, Chuchu and Chen, Ziliang and Xu, Weixiang and Li, Fanrong and others},
        journal={arXiv preprint arXiv:2406.03459},
        year={2024}
    }