Hi, I’m trying to implement this - GitHub - yinguobing/head-pose-estimation: Head pose estimation by TensorFlow and OpenCV , 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