Jacob Stern
Reputation: 4597
AttributeError: 'Tensor' has no attribute: 'backwards'
I'm posting this question for those who made the same error I did. I got this error when trying to compute my gradients:
criterion = torch.nn.CrossEntropyLoss()
loss = criterion(y_hat, y_truth)
loss.backwards()
Upvotes: 14
Views: 7569
Answers (1)
Related Questions
- RuntimeError occurs in PyTorch backward function
- TypeError: cross_entropy_loss(): argument ‘input’ (position 1) must be Tensor, not Linear
- Attribute Error: `loss.backward()` returns None
- loss.backward() no grad in pytorch NN
- TypeError: backward() got an unexpected keyword argument 'grad_tensors' in pytorch
- Pytorch error when computing loss between two tensors. TypeError: __init__() takes 1 positional argument but 3 were given
- Pytorch training loss function throws: "TypeError: 'Tensor' object is not callable"
- TypeError: 'int' object is not callable in loss.backward()
- AttributeError: 'Tensor' object has no attribute 'numpy' in custom loss function (Tensorflow 2.1.0)
- Setting custom loss causes RuntimeError: Variable data has to be a tensor, but got Variable in Pytorch