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

DeConv training? #3

Open
deepalianeja opened this issue Apr 27, 2016 · 5 comments
Open

DeConv training? #3

deepalianeja opened this issue Apr 27, 2016 · 5 comments

Comments

@deepalianeja
Copy link

I have a trained model and I'm trying your pipeline for unspooling and visualizing the layers. Do I need a new train_val.protxt? Do I need to train again with the DeConv layers? I have updated my deploy.prototxt. Can you please help?
@deepalianeja
Copy link
Author

My pre-trained model is similar to Alexnet in Caffe.

@mariolew
Copy link
Owner

You don't need to train with the DeConv layer, you only need to make the deploy file the similar way as my example.

@mariolew
Copy link
Owner

mariolew commented Apr 27, 2016 •
edited
Loading

@deepalianeja Please refer to examples/deconv_deploy.prototxt and examples/unpooling.ipynb for detail

@deepalianeja
Copy link
Author

Okay. Thanks.

It was looking for conv1t layers and other DeConv laters from the model so I got confused.

Do you also have an example of guided back propagation? I see something but is that complete?

@mariolew
Copy link
Owner

@deepalianeja Well, as for the guided back propagation, I think the example just did the right thing but in an ugly way. Do you also think so?

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
@deepalianeja @mariolew