📘Documentation | 🛠️Installation | 👀Model Zoo | 🚀Awesome DETR | 🆕News | 🤔Reporting Issues
detrex is an open-source toolbox that provides state-of-the-art Transformer-based detection algorithms. It is built on top of Detectron2 and its module design is partially borrowed from MMDetection and DETR. Many thanks for their nicely organized code. The main branch works with Pytorch 1.10+ or higher (we recommend Pytorch 1.12).
Major Features
-
Modular Design. detrex decomposes the Transformer-based detection framework into various components which help users easily build their own customized models.
-
State-of-the-art Methods. detrex provides a series of Transformer-based detection algorithms, including DINO which reached the SOTA of DETR-like models with 63.3mAP!
-
Easy to Use. detrex is designed to be light-weight and easy for users to use:
- LazyConfig System for more flexible syntax and cleaner config files.
- Light-weight training engine modified from detectron2 lazyconfig_train_net.py
Apart from detrex, we also released a repo Awesome Detection Transformer to present papers about Transformer for detection and segmentation.
The repo name detrex has several interpretations:
-
detr-ex : We take our hats off to DETR and regard this repo as an extension of Transformer-based detection algorithms.
-
det-rex : rex literally means 'king' in Latin. We hope this repo can help advance the state of the art on object detection by providing the best Transformer-based detection algorithms from the research community.
-
de-t.rex : de means 'the' in Dutch. T.rex, also called Tyrannosaurus Rex, means 'king of the tyrant lizards' and connects to our research work 'DINO', which is short for Dinosaur.
v0.1.1 was released on 18/10/2022:
- Add model analysis tools and benchmark in tools.
- Support visualization on COCO eval results and annotations in tools
- Support Group-DETR.
- Release more DINO training results including
DINO-R50-24epochs,DINO-R101,DINO-Swin-Tiny,DINO-Swin-Small,DINO-Swin-Base,DINO-Swin-Largein DINO. - Release better
Deformable-DETRbaselines with 48.2 AP on COCO dataset in Deformable-DETR.
Please see changelog.md for details and release history.
Please refer to Installation Instructions for the details of installation.
Please refer to Getting Started with detrex for the basic usage of detrex. We also provides other tutorials for:
- Learn about the config system of detrex
- How to convert the pretrained weights from original detr repo into detrex format
- Visualize your training data and testing results on COCO dataset
- Analyze the model under detrex
- Download and initialize with the pretrained backbone weights
- Frequently asked questions
Please see documentation for full API documentation and tutorials.
Results and models are available in model zoo.
Supported methods
- DETR (ECCV'2020)
- Deformable-DETR (ICLR'2021 Oral)
- Conditional-DETR (ICCV'2021)
- DAB-DETR (ICLR'2022)
- DAB-Deformable-DETR (ICLR'2022)
- DN-DETR (CVPR'2022 Oral)
- DN-Deformable-DETR (CVPR'2022 Oral)
- DINO (ArXiv'2022)
- Group-DETR (ArXiv' 2022)
- H-Deformable-DETR (ArXiv' 2022)
Please see projects for the details about projects that are built based on detrex.
This project is released under the Apache 2.0 license.
- detrex is an open-source toolbox for Transformer-based detection algorithms created by researchers of IDEACVR. We appreciate all contributions to detrex!
- detrex is built based on Detectron2 and part of its module design is borrowed from MMDetection, DETR, and Deformable-DETR.
If you find this project useful in your research, please consider cite:
@misc{ren2022detrex,
author = {Tianhe Ren and Shilong Liu and Hao Zhang and
Feng Li and Xingyu Liao and Lei Zhang},
title = {detrex},
howpublished = {\url{https://github.com/IDEA-Research/detrex}},
year = {2022}
}