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

Assignment 3 - Convolutional_Networks - kaiming_initializer function #1

Open

LanaKhalifa opened this issue May 25, 2023 · 0 comments

LanaKhalifa commented May 25, 2023 •

edited

Loading

Hello,
Thank you for the solution.

I think there are two errors in kaiming_initializer:

The calculated weights scale should be square rooted.
The calculated weight scale in the case of a convolutional layer, should be (gain/(DoutKK))(1/2), instead of (gain/(DinKK))(1/2). This is since, according to your implementation, Dout that you are feeding the kaiming initializer DeepConvNet init method, is the number of input dimensions.

I hope i am not mistaken,
Lana

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment