Feature Request: indices-based upsampling layer

[waissbluth]

Hello, does anyone have an implementation of this, or any thoughts on how to implement it?

Thanks

[preddy5]

Hey @waissbluth I didnt get enough time to work on it yet, I'll probably work on in a week or two.

[waissbluth]

Hey, is there anything I can do to help out with this? would really appreciate the feature.

[mpariente]

Hey, I would also love this feature! :)
Can I do anything to help?

Maybe a custom Maxpooling2D layer which produces an auxiliary output and an Upsample2D which would take an optionnal additionnal input would work?

[redouanelg]

Hi all, this guy implemented a class he called Depool2D, I'm not sure if it's what you are looking for https://github.com/nanopony/keras-convautoencoder/blob/master/autoencoder_layers.py

[mpariente]

Thanks for the link !
I saw it already and I have troubles understanding his DependentDense.
And also his DePool2D doesn't receive a switch from the MaxPooling2D if I read well.