How to run Head pose detection in TensorRT?

Hi, I’m trying to implement this - https://github.com/yinguobing/head-pose-estimation , to find head pose. The repo already has the model and essentials to run, and we can actually run it. but to increase the FPS, i wanted to run the program in TensorRT. How to implement this same repo to run with TensorRT?

Hello,

looks like headpose is a caffe model.

For converting Caffe model into TensorRT, here is document for your reference:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#import_caffe_python