https://github.com/kekmodel/MPL-pytorch/blob/7fb5b40cd53179bf4c09ef0f916815c3272d3e9d/main.py#L197 At this point hard_pseudo_label is a batch size by 1 array of integer indexes, not a one hot encoding. Is this correct when calculating cross entropy?
MPL-pytorch/main.py
Line 197 in 7fb5b40
At this point hard_pseudo_label is a batch size by 1 array of integer indexes, not a one hot encoding.
Is this correct when calculating cross entropy?