IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

[kkkkyp]

Traceback (most recent call last):
File "D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py", line 189, in
File "D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py", line 114, in fit
acc_val, loss_val, val_output = predict_(alg, model, label, loss_fn, val)
File "D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py", line 145, in predict_
batch_loss = loss_fn(batch_output, label[batch_edges])
File "D:\Anaconda\envs\GraphSAGE\lib\site-packages\torch\nn\modules\module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "D:\Anaconda\envs\GraphSAGE\lib\site-packages\torch\nn\modules\loss.py", line 948, in forward
ignore_index=self.ignore_index, reduction=self.reduction)
File "D:\Anaconda\envs\GraphSAGE\lib\site-packages\torch\nn\functional.py", line 2422, in cross_entropy
return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
File "D:\Anaconda\envs\GraphSAGE\lib\site-packages\torch\nn\functional.py", line 1591, in log_softmax
ret = input.log_softmax(dim)
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

Hello, can you help me solve this problem?

[George730]

you can add one more dimension to 'input', try input = torch.unsqueeze(input, 0).

[kkkkyp]

I try chage batch_loss = loss_fn(batch_output, label[batch_edges]) to
if len(batch_output.shape) == 1:
batch_output = torch.unsqueeze(batch_output,0)
batch_loss = loss_fn(torch.tensor(batch_output, dtype=torch.float32),
torch.FloatTensor(torch.tensor(label[np.array(batch_edges)], dtype=torch.float32)))
then, This error has occurred。
D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py:148: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
batch_loss = loss_fn(torch.tensor(batch_output, dtype=torch.float32),
D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py:149: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
torch.FloatTensor(torch.tensor(label[np.array(batch_edges)], dtype=torch.float32)))
Traceback (most recent call last):
File "D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py", line 189, in
fit(args)
File "D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py", line 114, in fit
acc_val, loss_val, val_output = predict_(alg, model, label, loss_fn, val) File "D:/PyCharm/Py_project/E-ResGAT-master/fit_model.py", line 149, in predict_
torch.FloatTensor(torch.tensor(label[np.array(batch_edges)], dtype=torch.float32)))
File "D:\Anaconda\envs\gsage\lib\site-packages\torch\nn\modules\module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "D:\Anaconda\envs\gsage\lib\site-packages\torch\nn\modules\loss.py", line 948, in forward
ignore_index=self.ignore_index, reduction=self.reduction)
File "D:\Anaconda\envs\gsage\lib\site-packages\torch\nn\functional.py", line 2422, in cross_entropy
return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
File "D:\Anaconda\envs\gsage\lib\site-packages\torch\nn\functional.py", line 2216, in nll_loss
.format(input.size(0), target.size(0)))
ValueError: Expected input batch_size (1) to match target batch_size (500).