RuntimeError: "bitwise_and_cpu" not implemented for 'Float' in DiceLoss

[agrizzli]

I am using:

• Python 3.8.10
• torch 1.12.0+cu113

When setting alpha > 0 in DiceLoss it results in following error:

RuntimeError: "bitwise_and_cpu" not implemented for 'Float' in DiceLoss

at line:

https://github.com/ShannonAI/dice_loss_for_NLP/blob/master/loss/dice_loss.py#L120

This is due to wrong operator evaluation order. First & is evaluated, which is wrong. You can avoid it by adding brackets around boolean operations:

cond = ((torch.argmax(flat_input, dim=1) == label_idx) & (flat_input[:, label_idx] >= threshold)) | pos_example.view(-1)

[sfdeggb]

I also meet this problem!, it is so hard to slove!