Jupyter Notebook (python version 3.9.0) PyTorch > RuntimeError: expected scalar type Long but found Int

[RamseyThomson]

In investigating CNNs, I have copied an online script into Jupyter Notebook (setup works fine) but:

defining the number of epochs

n_epochs = 25

empty list to store training losses

train_losses = []

empty list to store validation losses

val_losses = []

training the model

for epoch in range(n_epochs):
print('train for epoch:', epoch)
train(epoch)

At the first call to train(epoch) a runtime error is caused:

Line 2846 of ~\anaconda3\lib\site-packages\torch\nn\functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
results in > RuntimeError: expected scalar type Long but found Int
The above is called from line 1150 of ~\anaconda3\lib\site-packages\torch\nn\modules\loss.py in forward(self, input, target) which in turn is called from line 1102 of ~\anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)

Should I report this to the supplier of the online CNN example or have I discovered a bug?

[7ENG1Z]

HI,did you solve the problem?