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

GPU Memory #12

Closed superxi closed 3 years ago

superxi commented 3 years ago

Hi : I‘m wondering how much GPU memory is needed for training with batch size 1. I'm training with 2080Ti 11G, It always CUDA out of memory even when batch size is 1

fsybigman commented 3 years ago

try ReLU(inplace=True)

Jisu-Kang commented 3 years ago

I have a same problem. Did you solved this problem?