Using a target size (torch.Size([64])) that is different to the input size (torch.Size([64, 1]）

[Leo-Repo]

Text-Classification-LSTMs-PyTorch/main.py

Line 89 in 2f8bada

loss = F.binary_cross_entropy(y_pred, y)

Hello,
First I got a ValueError: Using a target size (torch.Size([64])) that is different to the input size (torch.Size([64, 1])) is deprecated. Please ensure they have the same size.
Then I altered y_pred to y_pred.squeeze().detach(), but I got a new error showing element 0 of tensors does not require grad and does not have a grad_fn where in line 93, loss.backward().
So can you help me? what should I do?

[NivNagli]

@bajixing Add at main.py after line 85 the next code line : y = y.unsqueeze(1), will solve out the problem for you.