search

yzxing87 / pytorch-deep-video-prior

[NeurIPS 2020] Blind Video Temporal Consistency via Deep Video Prior
118 stars 22 forks source link

CUDA out of memory #8

Closed semel1 closed 2 years ago

semel1 commented 2 years ago

I noticed that a similar issue has been closed. However, I have the same problem. So, "You can also load the frame just before each iteration. I think torch.utils.data.DataLoader can be a better option for this issue. We will update the code using pytorch dataloader." Any code update? Could you please provide me with more detail on how to " load the frame just before each iteration"

yzxing87 commented 2 years ago

Hi, I mean, in line 136-141 of main_IRT.py, we load the whole video into memory for accelerating training. You can also load the data just before each iteration, by changing line 162 and line 168.