RuntimeError: Found dtype Long but expected Float

[Dyongh613]

File "train.py", line 122, in main
model_update(model, step, G_loss, optG_fs2)
File "train.py", line 77, in model_update
loss = (loss / grad_acc_step).backward()
File "C:\Users\12604\Anaconda3\envs\pytorch\lib\site-packages\torch\tensor.py", line 221, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "C:\Users\12604\Anaconda3\envs\pytorch\lib\site-packages\torch\autograd_init_.py", line 132, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: Found dtype Long but expected Float

Hi@keonlee9420. This problem occurs when the loss function is back-propagating, how can I solve it?
This is the dtype of loss

[Dyongh613]

Hi@keonlee9420, this problem has been solved!
The previously passed parameters are also of type float when I debug them, but I don't know why this problem occurs.
I try to add the loss = loss.type(torch.FloatTensor), then it can pass successfully

[Frei2]

@Dyongh613 Can I ask that whether you train this model (portaspeech) under windows system?