I am following the guide to convert TensorFlow model to TensorRT using this doc: https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#import_tf_python
I have converted TensorFlow’s frozen graph to UFF successfully, but when I run the code shown in step 5, I get a segfault.
I saved the core dump file but there is no symlink-- I have tried to read symlink from “trtexec” from “/opt/tensorrt/bin/” directory in tensorRT nvidia docker, but it didn’t help.
I have attached frozen graph file, uff file, and code I used to convert uff to tensorrt but segfaulted.
- what would be a problem?
tensorrt_files.zip (15 MB)