Kevin Chen

Results 88 comments of Kevin Chen

This looks like an issue building on Windows, we don't officially support building on Windows yet. Marking as enhancement.

Can you provide a code snippet of your existing TensorRT workflow and how you are adding the argmax operator?

Not publicly yet. We are working on this functionality, will come later in a future release.

Can you give some more information on how you have TensorRT installed? I'm unable to repro the issue locally. My steps: Pull and run 22.02 TensorRT docker image: `docker pull...

Have you tried building with the tar method?

This should be fixed on the latest main branch for TRT 8.2. Can you update your TensorRT version and try to parse your model again?

Thanks for narrowing it down to a opset 13 issue. I'll take a look to see what's going on.