Skip to content

Conversation

@anubhavmaity
Copy link

@anubhavmaity anubhavmaity commented Mar 31, 2024

Two changes

  • Currently we are passing nn.BatchNorm as class not instance, therefore isinstance will not work. We have to compare nn.BatchNorm as class
  • Currently we reset losses, accuracy, and ns before each fit. It should be done at the start of every epoch instead.

@review-notebook-app
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@anubhavmaity anubhavmaity changed the title reset before every epoch instead before every fit check norm as class not instance & reset before every epoch instead before every fit Apr 28, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant