search

mariolew / caffe-unpooling

Caffe with unpooling layers and example usage.
Other
18 stars 11 forks source link

DeConv training? #3

Open deepalianeja opened 8 years ago

deepalianeja commented 8 years ago

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 commented 8 years ago

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

mariolew commented 8 years ago

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 commented 8 years ago

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

deepalianeja commented 8 years ago

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 commented 8 years ago

@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?