MMYOLO is an open source toolbox for YOLO series algorithms based on PyTorch and [MMDetection](https://github.com/open-mmlab/mmdetection). It is a part of the [OpenMMLab](https://openmmlab.com/) project.
MMYOLO unifies the implementation of modules in various YOLO algorithms and provides a unified benchmark. Users can compare and analyze in a fair and convenient way.
MMYOLO provides rich documentation for getting started, model deployment, advanced usages, and algorithm analysis, making it easy for users at different levels to get started and make extensions quickly.
MMYOLO decomposes the framework into different components where users can easily customize a model by combining different modules with various training and testing strategies.
We are excited to announce our latest work on real-time object recognition tasks, **RTMDet**, a family of fully convolutional single-stage detectors. RTMDet not only achieves the best parameter-accuracy trade-off on object detection from tiny to extra-large model sizes but also obtains new state-of-the-art performance on instance segmentation and rotated object detection tasks. Details can be found in the [technical report](https://arxiv.org/abs/2212.07784). Pre-trained models are [here](configs/rtmdet).
MMYOLO currently only implements the object detection algorithm, but it has a significant training acceleration compared to the MMDeteciton version. The training speed is 2.6 times faster than the previous version.
💎 **v0.3.0** was released on 8/1/2023:
1. Implement fast version of [RTMDet](https://github.com/open-mmlab/mmyolo/blob/dev/configs/rtmdet/README.md). RTMDet-s 8xA100 training takes only 14 hours. The training speed is 2.6 times faster than the previous version.
2. Support [PPYOLOE](https://github.com/open-mmlab/mmyolo/blob/dev/configs/ppyoloe/README.md) training
3. Support `iscrowd` attribute training in [YOLOv5](https://github.com/open-mmlab/mmyolo/blob/dev/configs/yolov5/crowdhuman/yolov5_s-v61_8xb16-300e_ignore_crowdhuman.py)
4. Support [YOLOv5 assigner result visualization](https://github.com/open-mmlab/mmyolo/blob/dev/projects/assigner_visualization/README.md)
MMYOLO relies on PyTorch, MMCV, MMEngine, and MMDetection. Below are quick steps for installation. Please refer to the [Install Guide](docs/en/get_started.md) for more detailed instructions.
MMYOLO is based on MMDetection and adopts the same code structure and design approach. To get better use of this, please read [MMDetection Overview](https://mmdetection.readthedocs.io/en/latest/get_started.html) for the first understanding of MMDetection.
The usage of MMYOLO is almost identical to MMDetection and all tutorials are straightforward to use, you can also learn about [MMDetection User Guide and Advanced Guide](https://mmdetection.readthedocs.io/en/3.x/).
For different parts from MMDetection, we have also prepared user guides and advanced guides, please read our [documentation](https://mmyolo.readthedocs.io/zenh_CN/latest/).
- [Algorithm principles and implementation](https://mmyolo.readthedocs.io/en/latest/algorithm_descriptions/index.html#algorithm-principles-and-implementation)
Please refer to the [FAQ](docs/en/notes/faq.md) for frequently asked questions.
## Contributing
We appreciate all contributions to improving MMYOLO. Ongoing projects can be found in our [GitHub Projects](https://github.com/open-mmlab/mmyolo/projects). Welcome community users to participate in these projects. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
## Acknowledgement
MMYOLO is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedback.
We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new detectors.
