This project base on https://github.com/Megvii-BaseDetection/YOLOX and https://zhuanlan.zhihu.com/p/391693130
Adapt the new version of YOLOX original pre-training model, FPS > 100 - 2021-12-20
Deploy yolox to deep stream, FPS > 70 - 2021-7-21
cuda 11.0+
TensorRT 8+
OpenCV 4.0+ (build with opencv-contrib module) how to build
OpenMP
DeepStream 6.0+
Make sure you had install dependencies list above
# clone project and submodule
git clone {this repo}
cd {this repo}/nvdsinfer_custom_impl_yolox/
make
use to parse infer postprocess.
cd {this repo}
deepstream-app -c deepstream_app_config.txt
https://zhuanlan.zhihu.com/p/391693130
For the 3rd-party module and Deepstream, you need to follow their license
For the part I wrote, you can do anything you want