weiwei zhou

alert("xss")

Yes, I deploy it to triton, the inference time is 4 ms on T4.

You can follow the documentation. https://github.com/triton-inference-server/server/blob/r20.12/README.md#documentation

tensorrt 阙豆林 ***@***.***> 于2021年5月20日周四 上午11:21写道： > 你好，我想问下您部署到trtion inference server是用得tensorrt还是torchscript > > — > You are receiving this because you were mentioned. > Reply to this email directly, view it on...

这个是对应yolov5-3.1版本的，先确保版本一致

dims: [1] reshape: { shape: [] } xiaoxuesheng ***@***.***>于2022年4月27日 周三19:48写道： > 请问count的dims 是多少，谢谢 > > — > Reply to this email directly, view it on GitHub > , > or...

nms层不会量化

You need to read the paper. henbucuoshanghai ***@***.***> 于2021年5月18日周二 下午9:48写道： > — > You are receiving this because you are subscribed to this thread. > Reply to this email directly,...

What's your build env? gcc, nvcc, tensorrt, cuda version?

You can try docker image nvcr.io/nvidia/tensorrt:21.06-py3