Skip to content

lab2-PT-MNIST: fix train() to use parameters rather than global values #208

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
spazm wants to merge 1 commit into
base: master
Choose a base branch
from
Open

lab2-PT-MNIST: fix train() to use parameters rather than global values #208

spazm wants to merge 1 commit into from

Conversation

@spazm
Copy link

@spazm spazm commented Jan 8, 2026 •
edited
Loading

  • global values fc_model and loss_function were used inside the train() function rather than the passed parameters model and criterion.
  • duplicates fix in both the student and solution versions of the pytorch notebook.
@spazm
lab2-PT-MNIST: fix train() to use parameters rather than global values
3f60f4d 
+ global values `fc_model` and `loss_function` were used inside the train()
  function rather than the passed parameters `model` and `criterion`.
+ fix duplicated in both the student and solution versions of the pytorch
  notebook.
@spazm
Copy link
Author

spazm commented Jan 9, 2026 •
edited
Loading

See also #195 which catches a third issue with the dataloader and #199 which combines all three fixes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant

@spazm