Skip to content

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

License

Notifications You must be signed in to change notification settings

feat7/YOLOX

 
 

Repository files navigation

YOLOX: Quick tool for running some object detection experiments.

Original repo and yolox_s.pth location: YOLOX

How to run

  • Convert your dataset in coco format.
  - dataset_directory/
    - images/
     - image1.jpg
     - abcfdtD.jpg
     - ...
    - annotations/
      - train_coco.json
      - val_coco.json
  • Modify exps/yolox_s_logy.py

  • OR you can also run python pipeline/setup.py after modifying pipeline/config.json

  • Run ./train_pipeline.sh to train the file

About

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 92.2%
  • C++ 7.5%
  • Other 0.3%