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

Seems that there's no use of any 'crf' folders. #6

Open
deshelv opened this issue Mar 22, 2016 · 2 comments
Open

Seems that there's no use of any 'crf' folders. #6

deshelv opened this issue Mar 22, 2016 · 2 comments

Comments

@deshelv
Copy link

deshelv commented Mar 22, 2016

Seems that there's no use of any 'crf' folders. Does it mean that there are no crf features generated?
Also curious about why using tool.saver() to save the model and there's no deploy.prototxt.
@TheLegendAli
Copy link
Owner

crf folders: we have to redo the way the paths are done
The question to last two question is inheritance reasons. we tried to keep it as consistent as the original deeplab. the deploy.prototxt is easy to made from train prototxt if you have a problem creating it i will post one for you.

@zhangjingling
Copy link

what does is it mean ？

We have also provided a wrapper for Philipp's implementation in Caffe (see the layer densecrf_layer.cpp)

How to add the denserf_layer?

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
3 participants
@TheLegendAli @deshelv @zhangjingling