search

maum-ai / faceshifter

Unofficial PyTorch Implementation for FaceShifter (https://arxiv.org/abs/1912.13457)
BSD 3-Clause "New" or "Revised" License
610 stars 114 forks source link

Training Iterations #7

Closed CengizhanYurdakul closed 3 years ago

CengizhanYurdakul commented 3 years ago

Hello again, thanks for sharing code. I am trying to train. I have 200k dataset but tqdm shows process finish in 125 hours. Because 1 epoch need 2 millions 206k iterations. How may i change this?

usingcolor commented 3 years ago

Please see the #4. The number of training iteration in one epoch is very large, you can modify dataset or save checkpoint more often.