'nn.CorssEntropyLoss documentation example is not correct?
Tested the documentation example of nn.CrossEntropyLoss. It doesn't seem to work.
loss = nn.CrossEntropyLoss()
input = torch.randn(3, 5, requires_grad=True)
target = torch.randn(3, 5).softmax(dim=1)
output = loss(input, target)
print(output)
error:
RuntimeError: 1D target tensor expected, multi-target not supported
Solution 1:[1]
You might need to upgrade your torch version.
pip install torch --upgrade
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | joe32140 |