Mike Azatov

Is that a `markdown` and `importlib-metadata` compatability issue? In which case, which versions should I have?

Wonder the same thing @doraeric . As I understand the difference comes when the input image size is even and not odd, correct? So shouldn't we be able to load...

It looks like 'channel_shift_range` adds/subtracts the same intensity from all channels in the image. So because of that the image just becomes brighter or darker instead of changing color. I...

Any updates @KikuchiRyosuke? I have the same problem.

Interesting. I was just basing it on this line: ` ResNet18, preprocess_input = Classifiers.get('resnet18')`

What algorithm are you using to inflate the weights from 2D to 3D?

@WongKinYiu , has classification been added? Thanks!

@wvangansbeke, really appreciate you keeping up with the repository and replying. Great paper and very clear code. My dataset is quite imbalanced. ~ 250000 samples, 5 classes, the largest class...

@wvangansbeke , what do you mean by `randaugment.py` ? Are you referring to the `data\augment.py` ? I switched the augmentations for my data by changing this `augment_list` [here](https://github.com/wvangansbeke/Unsupervised-Classification/blob/ac7abe0fbf27d363eb8b616bb08a11d295c7f0fa/data/augment.py#L79). Is there...

Thanks @wvangansbeke! One more question: I was doing some more debugging and found out the following. Two of my classes are somewhat similar. So let's out of five classes, Class...