larger_than_threshold

[LiuChen19960902]

UDA_pytorch/main.py

Line 88 in 0ba5cf8

larger_than_threshold = torch.exp(-sup_loss) > tsa_thresh # prob = exp(log_prob), prob > tsa_threshold

If both “larger_than_threshold” are True, then the value of "loss_mask" is 0 and sup_loss divided by 0 results in a loss of "nan"