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

Move Away from Assumption of just One Output Layer #158

Open

cancan101 opened this issue Sep 23, 2015 · 0 comments

Contributor

cancan101 commented Sep 23, 2015

Right now there are a number of places that assume one output layer:

nolearn/nolearn/lasagne/base.py

Line 395 in b4a4cb6

output_layer = layers[-1]
nolearn/nolearn/lasagne/base.py

Line 390 in b4a4cb6

return layer
Cleanup initialize and how it calls initialize_layers #157
nolearn/nolearn/lasagne/base.py

Line 143 in 409c5f5

output_layer = layers[-1]

It would be nice to break this assumption and leave it up to the writer of the loss / objective to deal with more than one output layer.

cancan101 mentioned this issue

Multiple network outputs #202

Closed

cancan101 mentioned this issue

Added visualization code using saliency maps #223

Merged

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