Converting uff_to_tensorRT_engine

Autonomous Machines Jetson & Embedded Systems Jetson Nano
1

Hi, I successfully trained and converted frozen_inference graph to uff file but I couldn’t figure out how to convert uff_to_tensorRT engine. Where is the uff_to_tensorRT_engine.py ? Which command I should use for this?

Thanks.

3

Hi,

You can convert the uff file with our binary directly:

$ /usr/src/tensorrt/bin/trtexec --uff=<file> --uffInput=<name>,X,Y,Z --output=<name>[,<name>]*

For python interface, please check this sample:

/usr/src/tensorrt/samples/python/end_to_end_tensorflow_mnist

Thanks.