Skip to content
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.

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

Is dropout disabled? #76

Open
nicolasrosa opened this issue Jul 30, 2018 · 1 comment
Open

Is dropout disabled? #76

nicolasrosa opened this issue Jul 30, 2018 · 1 comment

Comments

@nicolasrosa
Copy link

"Following the set of these up-sampling blocks, dropout is applied and succeeded by a final convolutional layer yielding the prediction."

However, in the fcrn.py code, the value of keep_prop is always equal to 1.

.dropout(name='drop', keep_prob=1.)

FIX:
.dropout(name='drop', keep_prob=self.keep_prob)

Is that correct?

@dagap
Copy link

dagap commented Mar 21, 2019

Dropout probabilistically keeps a neuron activated usually only during training time. I guess the code here is for inference, where the dropout keep probability is usually set to 1.0

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

No branches or pull requests

2 participants