How to see what UFF operations tensorrt supports

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Description

A clear and concise description of the bug or issue.

Environment

TensorRT Version: 6.0.1
GPU Type: jetson-tx2
CUDA Version: 10.0
Operating System + Version: ubuntu 18.04
Python Version (if applicable): 3.6

My tensorflow model has some operations that tensorrt does not support, so I use graphsurgeon to replace it. I want to know where to see what operations tensorrt supports

2

Hi,

Please refer to below link :
https://docs.nvidia.com/deeplearning/sdk/tensorrt-archived/tensorrt-700/tensorrt-api/python_api/uff/Operators.html

Also, we are deprecating Caffe Parser and UFF Parser in TensorRT 7. Will recommend to user ONNX parser for TRT engine model generation.
https://github.com/onnx/onnx-tensorrt/blob/master/operators.md

Thanks

3

Thank you for your quick reply, which is very helpful to me