Ahmed Mustahid

Results 4 comments of Ahmed Mustahid

You have to get the docker container with the required torch version

I have been facing the same issue while using ncnn backend. `Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when...

Exactly. I hope they address the issue.

I have been facing the same issue. `/usr/src/tensorrt/bin/trtexec --onnx=./end2end.onnx --plugins=../../mmdeploy/lib/libmmdeploy_tensorrt_ops.so --workspace=6000 --fp16 --saveEngine=end2end.engine` does not work either and gives the following error: ``` 03/06/2023-21:52:55] [W] [TRT] onnx2trt_utils.cpp:366: Your ONNX model...