Abhirath Anand

Hi Vinayakjeet, thanks for the PR! Unfortunately, I don't think this does what we want yet. The problem is that `inchannels` isn't being passed to the model backbone. What you've...

Thank you for the bug report! I can reproduce this on my machine. The regression in times without the weights is something that is probably caused by more function calls...

> > This regression also seems to be happening on VGG for some reason. > > With or without loading the weights? With the weights. I'm sorry, I should have...

Right now, we don't export anything at the top level from `Layers` 😅 This is probably because at the time I felt the `Layers` module was always going to undergo...

Hi @nickkeepfer, as I understand it, the way U-Net is being constructed right now requires you to specify `inchannels` at two places - one for the function itself and another...

Yeah, it's definitely weird to keep it this way, I will try and land a PR soon to address this.

I think most of the readability question can easily be addressed by good docs. I was short on time and secretly hoping that Pollen would be more mature by the...

I think the Inception errors are because that family of models use an image size of 299x299, and I don't think they support alternate image sizes. AlexNet uses 224x224 and...