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

resblock - bias of both convolutions can be set to False, since batch normalization is applied afterwards #21

Open

dvorst opened this issue Feb 4, 2022 · 0 comments

dvorst commented Feb 4, 2022

In resblock, the bias of both convolutions can be set to False, since batch normalization is applied afterwards.

MSRF-Net/model.py

Lines 50 to 51 in 60e2373

    
           out = Conv2D(op_channels,kernel_size=(3,3),strides=stride,padding='same')(x) 
        
           out = BatchNormalization()(out)

MSRF-Net/model.py

Lines 53 to 54 in 60e2373

    
           out = Conv2D(op_channels,kernel_size=(3,3),strides=stride,padding='same')(x) 
        
           out = BatchNormalization()(out)

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