Quantizing the model #36
Description
Hi, my group used this GitHub repository to do a project on face recognition. We want to run the model and TensorFlow code on ZCU102 board, but it requires the model to be quantized, and I am having problem in quantizing the model. Anyone has achieved in quantizing the model (.pb file) or running this model and python code (TensorFlow) on ZCU101 board before?
Really appreciate your help, and thank you in advanced.