Hi, I want to reproduce your performance.

[easternCar]

I used face alignment to original CASIA and LFW to prepare aligned datasets using code from https://github.com/ZhaoJ9014/face.evoLVe.PyTorch (align/face_align.py). However, after training, my accuracy on LFW recorded 96.4833 %. When I tried to search the problem, people are saying that the alignment can be major causes on performance.

I wonder what alignment code you used. I also refernece the code (https://github.com/wujiyang/Face_Pytorch) but the owner of that Github page doesn't seem to be active in answering now.