metrics.py invokes torch.max with "an invalid combination of arguments "

[gsgbills]

---

TypeError Traceback (most recent call last)
in ()
----> 1 accuracy(*learn.TTA())

~/fastai/courses/dl1/fastai/metrics.py in accuracy(preds, targs)
3
4 def accuracy(preds, targs):
----> 5 preds = torch.max(preds, dim=1)[1]
6 return (preds==targs).float().mean()
7

TypeError: torch.max received an invalid combination of arguments - got (numpy.ndarray, dim=int), but expected one of:

• (torch.FloatTensor source)
• (torch.FloatTensor source, torch.FloatTensor other)
  didn't match because some of the keywords were incorrect: dim
• (torch.FloatTensor source, int dim)
• (torch.FloatTensor source, int dim, bool keepdim)

[gsgbills]

This maybe the same issue as #115 .

[gsgbills]

arguments should be cast, e.g., torchLongTensor(targs)

[jph00]

Let's move the discussion to #115 . We'll need more info about where you're calling the function from to fix this properly, BTW.