Hi,
I have a model trained in tensorflow and see the same inference speed for FP32 in tensorflow and after TRT conversion. How can I go about debugging why there is no speedup?
I should say this is actually v5.1
Hi,
I have a model trained in tensorflow and see the same inference speed for FP32 in tensorflow and after TRT conversion. How can I go about debugging why there is no speedup?
I should say this is actually v5.1