FocalLoss binary not working, is it because of masks?

[Harsh-Gill]

I am trying foccal loss but it doesnt work.

raise ValueError("Target size ({}) must be the same as input size ({})".format(target.size(), input.size()))

ValueError: Target size (torch.Size([524288])) must be the same as input size (torch.Size([1048576]))

This error is shown but when i try the torch.nn.CrossEntropy(pred,true) , it works fine.

Is this because FocalLoss like other losses dont work for mask-based learning?