RT-DETR/rtdetrv2_pytorch/configs/rtdetr/readme.md

DETRs Beat YOLOs on Real-time Object Detection

Introduction

This repository is the official pytorch implementation of RTDETR, and is compatiable with RT-DETR/rtdetr_pytorch. For paddle version implementation, please refer to RT-DETR/rtdetr_paddle. If you are using rtdetr for the first time, it is highly recommended to use rtdetrv2.

Fig

Model Zoo

Model	Dataset	Input Size	APval	AP50val	#Params(M)	FPS	checkpoint
rtdetr_r18vd	COCO	640	46.4	63.7	20	217	url*
rtdetr_r34vd	COCO	640	48.9	66.8	31	161	url*
rtdetr_r50vd_m	COCO	640	51.3	69.5	36	145	url*
rtdetr_r50vd	COCO	640	53.1	71.2	42	108	url*
rtdetr_r101vd	COCO	640	54.3	72.8	76	74	url*
rtdetr_18vd	COCO+Objects365	640	49.0	66.5	20	217	url*
rtdetr_r50vd	COCO+Objects365	640	55.2	73.4	42	108	url*
rtdetr_r101vd	COCO+Objects365	640	56.2	74.5	76	74	url*

Notes

• COCO + Objects365 in the table means finetuned model on COCO using pretrained weights trained on Objects365.
• FPS is evaluated on a single T4 GPU with batch\\_size = 1 and tensorrt\\_fp16 mode
• url* is the url of the pretrained weights, converted from the paddle model to save energy. *There may be slight differences between this table and the paper.

Usage

details

1. Training

CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun --master_port=9909 --nproc_per_node=4 tools/train.py -c path/to/config &> log.txt 2>&1 &

2. Testing

CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun --master_port=9909 --nproc_per_node=4 tools/train.py -c path/to/config -r path/to/checkpoint --test-only

3. Tuning

CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun --master_port=9909 --nproc_per_node=4 tools/train.py -c path/to/config -t path/to/checkpoint &> log.txt 2>&1 &

4. Export onnx

python tools/export_onnx.py -c path/to/config -r path/to/checkpoint --check

5. Inference

Support torch, onnxruntime, tensorrt and openvino, see details in references/deploy

python references/deploy/rtdetrv2_onnx.py --onnx-file=model.onnx --im-file=xxxx
python references/deploy/rtdetrv2_tensorrt.py --trt-file=model.trt --im-file=xxxx
python references/deploy/rtdetrv2_torch.py -c path/to/config -r path/to/checkpoint --im-file=xxx --device=cuda:0

Citation

If you use RTDETR in your work, please use the following BibTeX entries:

bibtex

@misc{lv2023detrs,
      title={DETRs Beat YOLOs on Real-time Object Detection},
      author={Wenyu Lv and Shangliang Xu and Yian Zhao and Guanzhong Wang and Jinman Wei and Cheng Cui and Yuning Du and Qingqing Dang and Yi Liu},
      year={2023},
      eprint={2304.08069},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@software{Lv_rtdetr_by_cvperception_2023,
author = {Lv, Wenyu},
license = {Apache-2.0},
month = oct,
title = {{rtdetr by cvperception}},
url = {https://github.com/lyuwenyu/cvperception/},
version = {0.0.1dev},
year = {2023}
}