IndexError: Dimension out of range(expected to be in range of [-1, 0], but got 1)
hyuan1991 opened this issue · comments
Hey, I got this error when I was trying to fine tune on CIFAR 10 dataset.
I got the same error when I was trying to fine tune on my own dataset.
Anyone got the same error?
Thanks
Hey, I got this error when I was trying to fine tune on CIFAR 10 dataset. I got the same error when I was trying to fine tune on my own dataset.
Anyone got the same error?
Thanks
Change two places:
(1) line 193:
import torch.nn.functional as F
output = model(x)
loss = F.cross_entropy(output, y)
(2) line 106:
logits = model(x)
Hope it can be helpful.
Change line 106 to logits = model(x) works.