search

FluxML / Flux.jl

Relax! Flux is the ML library that doesn't make you tensor
https://fluxml.ai/
Other
4.53k stars 609 forks source link

Add max/mean unpooling operations #395

Open AzamatB opened 6 years ago

AzamatB commented 6 years ago

These are fairly common operations in image2image models (including 3d images) where they go in hand with ConvTranspose layers.

MikeInnes commented 6 years ago

I'm on board; I think it'd make sense to add them to NNlib. If there are any volunteers I'd be happy to look at a PR.

bhvieira commented 4 years ago

What is meant by max/mean-unpooling? Is it meant like in the U-Net where you return the max value to the position it was found in the descending path? I would like something like that, but I'm not sure we can do that without binding the downscaling and upscaling pooling layers.

darsnack commented 3 years ago

Anymore clarity on this? My interpretation is that it is just #1468 in which case we can close.

DhairyaLGandhi commented 3 years ago

No unpooling is slightly different. Check the pytorch layer with the same name

kraftpunk97 commented 3 months ago

Has this issue been addressed? Can I claim this?