Skip to content

Add missing update for conv2d_layer #141

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
Merged
merged 1 commit into from
Jun 15, 2023
Merged

Add missing update for conv2d_layer #141

merged 1 commit into from
Jun 15, 2023

Conversation

@milancurcic
Copy link
Member

@milancurcic milancurcic commented Jun 15, 2023

Conv2d layers were previously not getting their parameters updated during training. cnn_mnist now converges.

@milancurcic milancurcic added the bug Something isn't working label Jun 15, 2023
@milancurcic
Copy link
Member Author

milancurcic commented Jun 15, 2023

cnn_mnist converges with or without this fix but to a relatively low accuracy (~93% in 10 epochs), whereas it should easily get to >98%. While the fix introduced in this PR is necessary for updating conv2d layers to work, there is another bug elsewhere that is causing bias and weight gradients to remain zero during training.

@milancurcic milancurcic merged commit e34671e into modern-fortran:main Jun 15, 2023
@milancurcic milancurcic deleted the fix-conv2d-update branch June 15, 2023 14:54
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

bug Something isn't working

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@milancurcic