Wang Xinyu

@vobecant thanks for your python implementation, I use it in my repo [wang-xinyu/csp.pytorch](https://github.com/wang-xinyu/csp.pytorch). which is a pytorch reimplementation of csp.

@wdhao was using a custom model, but the code can still be referenced. @abhiagwl4262 If you can adapt the code to make it work with the pretrained model, then welcome...

https://github.com/wang-xinyu/tensorrtx/issues/966#issuecomment-1186742852

yes

Environment issue, the cudnn, tensorrt, cuda, etc, are not properly installed.

Are you using the pretrained model provided by them or your own trained model? And have you tried v.6.0?

If the result is acceptable, you can try to compare the mAP.

The error is from deepstream, not from gen_wts.py. And deepstream integration is not within the scope of this repo.

I remember yolov6 itself already supported trt. Any reason why we need to implement it again?

Not planned yet, welcome any PR for the same.