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.

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

Configurate Convolutional Auto-Encoders in Caffe #1647

Closed
pl8787 opened this issue Dec 29, 2014 · 2 comments
Closed

Configurate Convolutional Auto-Encoders in Caffe #1647

pl8787 opened this issue Dec 29, 2014 · 2 comments

Comments

@pl8787
Copy link

pl8787 commented Dec 29, 2014

Does anyone know how to config Convolutional Auto-Encoders in Caffe? And is it useful for initialize the CNN parameters?
Ref: Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
@pl8787
Copy link
Author

pl8787 commented Jan 4, 2015

Does anyone know about this issue?

@shelhamer
Copy link
Member

The encoder part is easily defined in Caffe as-is, but the decoder needs unpooling, deconvolution #1615, and transposed inner product layers that are not currently in the public BVLC/caffe.

Please ask modeling questions on the caffe-users mailing list. Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@shelhamer @pl8787