Nate Meyer

No that is a new one to me. I'll see what I can dig up later today.

I'm not opposed to having the support for v10 in here, there will come a day we need to upgrade TensorRT to support newer cards. I'm a little unsure of...

> My suggestion to reduce code duplication would be to check TRT_VERSION before every tensorRT api call that has changed (`binding_is_input`, `get_binding_shape` and `get_binding_dtype`). This would increase the number of...

If we are dropping NCS support, I think we can switch to the official packages of OpenVINO. PyPi now has packages for MacOS and Aarch64 in addition to x64 https://pypi.org/project/openvino/...

I think that driver version is ok. It's weird we're just seeing these issues with the Kx2 "Maxwell" Quadro cards. I wonder if there are issues with the compute 5.0...

TensorRT 8.5.3 claims to support compute 5.0, but I don't have one of those cards to test with. Do we know of anyone with a Maxwell GPU that is running...

> > this should be fixed in the next version, based on the linked PR above > > Oh awesome! I didn't see that. I will look out for that...

I'll take a closer look and try to run this later today. Do you have any insight on the differences between this and the yolov4 models?

The model input can be fixed by seeing `input_tensor: nchw`, but the OpenVino detector expects the output tensor to be an SSD format and will error out with the YoloX...

I notice the person detect model has a label always of 0 for `person`. Try passing in a new label map with just one line: ```txt person ```