Face_Pytorch
Face_Pytorch copied to clipboard
output of arcface loss function different to mxnet original Implementation
Hello, I tested the output of your arcface loss function and compared it to the original implementation of Insightface (mxnet). I gave them the loss weights as a parameter. Unfortunately the output obtained is not the same for both functions. You can find the script for comparing both functions in the following link: https://github.com/williamCorrea85/arcface/blob/master/arcface_comp_for_github.py
There are two mistakes in the script.
请问您使用预训练模型了吗? Have you used the pre training model?