Please provide the following information when requesting support.
• Hardware (T4)
• Network Type (Dino)
Hi i converted Dino model to FP32 , but the inference speed with batch size 1 is not satisfactory
I want to try some optimization technique using tao_toolkit
How can i do that ,
I was looking for pruning but there is not much good reference on how to do it for Dino
Can you please advice on this
4 posts - 2 participants