Custom BCEWithLogitsLoss for Sequence Classification using Auto Model

[John6666]

Hmm…

HELP with multilabel classification and BCEWithLogitsLoss

Mismatched target and input size for BCE using "multi_label_classification"

I am trying to build a multi-label, multi-class classification model. Any input text can have zero or more labels, up to 11 possible classes. I have been trying to use the problem_type="multi_label_classification" and everything looks OK, but I get ValueError: Target size (torch.Size([16, 11])) must be the same as input size (torch.Size([16, 2])) when it tries to calculate the binary_cross_entropy_with_logits I presume my data is in the wrong shape somehow, but I can’t see where exactly. Any s…

ValueError: Target size (torch.Size([32])) must be the same as input size...

BCEWithLogitsLoss is for Binary 0 or 1 use torch.nn.CrossEntropyLoss