Fails when batch is an odd number

[golunovas]

It seems like the issue is coming from here.

autoalbument/autoalbument/faster_autoaugment/search.py

Line 254 in dbeffa7

b = input.size(0) // 2

As far as I understand, it requires an even batch otherwise it fails here

autoalbument/autoalbument/faster_autoaugment/search.py

Line 201 in dbeffa7

interpolated = alpha * real + (1 - alpha) * fake

[creafz]

Hey, @golunovas

Could you please provide a use case for the odd batch_size? It seems that the best way to handle that problem is to include an explicit check into AutoAlbument which ensures that batch_size is an odd number before running a search phase. Otherwise, I think some problems related to the different number of augmented and not-augmented images may arise.

[golunovas]

Well, I ran into that issue on the last batch of the epoch when I just ran a search on the generated config search.yaml where drop_last wasn't set to true for the dataloader and I had an odd number of samples in the dataset. But the odd batch size will lead to exactly the same issue. IMO, the easiest solution is to set drop_last to true by default and require an even batch size to be set in the config.

[creafz]

I have added the drop_last: True parameter to config files created by autoalbument-create. Example configs now also contain this parameter. The fixed version 0.0.4 is also uploaded to PyPI.