Skip to content
This repository has been archived by the owner on Nov 28, 2023. It is now read-only.

[potential bug] #210

Open
LilySnow opened this issue Nov 17, 2020 · 0 comments
Open

[potential bug] #210

LilySnow opened this issue Nov 17, 2020 · 0 comments

Comments

@LilySnow
Copy link
Contributor

LilySnow commented Nov 17, 2020

From @manonreau on graphprot:

When you store loss values, do not forget to detach it from the computation graph (that is used for the back propagation) or you could run into memory issues ! :)
ex :

tot_loss += loss.item()          # DON'T DO THAT
tot_loss += loss.detach().item() # DO THAT :D

DeepRank is using:
running_loss += loss.data.item() in NeuralNet.py. Maybe we want to correct it.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant