exception thrown when nonzero_indices is empty

[hturki]

While training the model on a custom dataset I notice that I run into cases where nonzero_indices is empty and https://github.com/GuYuc/WS-DAN.PyTorch/blob/master/utils.py#L157 then throws an exception.

Is this behavior expected to happen? I'm guessing one could set:

                height_min = 0
                height_max = imgH
                width_min = 0
                width_max = imgW

when nonzero_indices

But I wanted to first confirm that I was understanding this code correctly and that nonzero_indices being empty wasn't symptomatic of a deeper issue.

[GuYuc]

@hturki Hi. Thank you for posting this question. I think this problem could happen if no value in attention map larger than the threshold, which could make all values in crop_mask become zeros. You may try to manually catch this exception and set them to (0, imgH) as you mentioned, or initialize attention conv layers appropriately to make sure it outputs some large values (maybe close to 1) in early stage of training.