Hi,

I find that BCELoss target require float tensor, which is wierd. It should accept LongTensor or IntTensor for a binary classification (0 or 1) right?

This is the error message I get.

TypeError: FloatBCECriterion_updateOutput received an invalid combination of arguments - got (int, torch.FloatTensor, torch.LongTensor, torch.FloatTensor, bool, NoneType), but expected (int state, torch.FloatTensor input, torch.FloatTensor target, torch.FloatTensor output, bool sizeAverage, [torch.FloatTensor weights or None])