关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>

XIONG131 14f7f270b3 更新 'train.py'		10 months ago
.github	enable test cases	10 months ago

configs	更新 'configs/coco.yaml'	10 months ago

demo	comply PEP-8 pycodestyle	1 year ago

deploy	update readme algin with deploy lite 2.0	11 months ago

docs	update installation.md docs	10 months ago

examples/finetune_SHWD	fix datasink mode accuracy zero bug.	11 months ago

mindyolo	更新 'mindyolo/utils/trainer_factory.py'	10 months ago

requirements	add test_create_loader	10 months ago

tests	add test_create_loader	10 months ago

tutorials	update huaweiyun tutorial	11 months ago

.gitignore	add gitignore	1 year ago

CONTRIBUTING.md	Add docs for getting started	1 year ago

GETTING_STARTED.md	add finetune tutorial	11 months ago

GETTING_STARTED_CN.md	add finetune tutorial	11 months ago

LICENSE.md	Add docs for getting started	1 year ago

MODEL_ZOO.md	update yolox l,x,darknet53 weight	11 months ago

README.md	update installation.md docs	10 months ago

README_CN.md	update installation.md docs	10 months ago

ma-pre-start.sh	update model's readme	1 year ago

mkdocs.yml	code style improve	11 months ago

package.sh	Add packaging code	1 year ago

requirements.txt	add fast coco eval api	10 months ago

setup.py	add fast coco eval api	10 months ago

test.py	add fast coco eval api	10 months ago

train.py	更新 'train.py'	10 months ago

yolov8-n.ckpt	重命名"yolov8-n_500e_mAP372-cc07f5bd.ckpt"为"yolov8-n.ckpt"	10 months ago

README.md

MindYOLO

MindYOLO

MindYOLO is MindSpore Lab's software toolbox that implements state-of-the-art YOLO series algorithms, support list and benchmark. It is written in Python and powered by the MindSpore AI framework.

The master branch supporting MindSpore 2.0.

What is New

2023/06/15

Support YOLOv3/v4/v5/X/v7/v8 6 models and release 23 corresponding weights, see MODEL ZOO for details.
Support MindSpore 2.0.
Support deployment on MindSpore lite 2.0.
New online documents are available!

Benchmark and Model Zoo

See MODEL ZOO.

Supported Algorithms

Installation

See INSTALLATION for details.

Getting Started

See GETTING STARTED for details.

Learn More about MindYOLO

To be supplemented.

Notes

⚠️ The current version is based on the static shape of GRAPH. The dynamic shape of the PYNATIVE will be supported later. Please look forward to it.

How to Contribute

We appreciate all contributions including issues and PRs to make MindYOLO better.

Please refer to CONTRIBUTING.md for the contributing guideline.

License

MindYOLO is released under the Apache License 2.0.

Acknowledgement

MindYOLO is an open source project that welcome any contribution and feedback. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible as well as standardized toolkit to reimplement existing methods and develop their own new realtime object detection methods.

Citation

If you find this project useful in your research, please consider cite:

@misc{MindSpore Object Detection YOLO 2023,
    title={{MindSpore Object Detection YOLO}:MindSpore Object Detection YOLO Toolbox and Benchmark},
    author={MindSpore YOLO Contributors},
    howpublished = {\url{https://github.com/mindspore-lab/mindyolo}},
    year={2023}
}