ONNX Issue

Open mayhemantt opened this issue 1 year ago • 1 comments

Hi, I tried to run this model on iOS (using core ml) works fine, but when I did it for Android with onnx, the inference time went high to 180ms, whereas it runs around 20-30 on ios.

I tired to look into onnx export and found there are some issues.

Has anyone faced the same and how to fix this?

May 02 '24 07:05 mayhemantt

@mayhemantt I had issues with the instancenorm when I exported to ONNX, I solved them by using onnx-simplifier, which allowed me to build an engine using tensorrt.

May 22 '24 13:05 ktadgh