Questions about using caffe-deconvnet

[w20ss11]

Thanks for releasing your excellent work. I have run the demo in the deconvnet-python-demo file folder ,and I got the outputs. The following pictures are originated from “pool5” as shown in your python code.

Besides, I want know how to get the deconvolutional outputs from other layers’ feature map. I have tried to change some code in line 68 of the test_deconv.py(change pool5 to pool4). However, I met some errors here.

In addition, Could you tell me how to use other models to perform deconvolution and draw the outputs?
Thank you very much.

[piergiaj]

You'll have to change the model defined in invnet.prototxt to start at the correct layer (for example, pool4 instead of pool 5), which should be as simple as deleting a few extra layers.

To make this work with other models, you'll have to create the inverse model file for it (like the invnet.prototxt file) and connect the switches and other inputs to the model.

[Pratyeka]

Thanks for your codes!I field to modify the new Caffe，got a lot of trouble, Where can I download the Caffe you used for deconvnet？3Q very much！

[GloryZhao]

Hello@w20ss11
I have the same problem with you.Have you already solved it ?And Can you give me some advises to work it out. 3Q very much.