TensorRT icon indicating copy to clipboard operation
TensorRT copied to clipboard

Published 20 hours ago • verified publisher icon NVIDIA

build int8 engine failed.

Open dulvqingyunLT opened this issue 2 years ago • 1 comments

Description

I created a model which has only one fully connected layer, and want to build it into int8 engine, but it turn out a fp32 engine file. Could anyone help me? Here is the script. test.py.zip

Steps To Reproduce

dulvqingyunLT avatar Sep 23 '22 06:09 dulvqingyunLT

You didn't specify the INT8 config flag. please refer to https://docs.nvidia.com/deeplearning/tensorrt/api/python_api/infer/Core/BuilderConfig.html#tensorrt.BuilderFlag and check our documentation carefully.

zerollzeng avatar Sep 24 '22 16:09 zerollzeng

closing since no activity for more than 3 weeks, please reopen if you still have question, thanks!

ttyio avatar Dec 06 '22 02:12 ttyio