RuntimeError: expand(torch.DoubleTensor{[694, 6]}, size=[694]): the number of sizes provided (1) must be greater or equal to the number of dimensions in the tensor (2)

[illustrious.felice]

Hello,

I am cloning the Q18 neural network example (LSTM) and running it. I noticed that when I leave the get_features function with only 1 feature, the model runs normally

I plan to use more features as follows:

And got the following error

Please show me how to fix the error so that I can apply more features. I only edited the get_features function, all the remaining code is the same as the Q18 neural network example

Please help me. Thank you so much.

[illustrious.felice]

@illustrious-felice Please help me fix this error. @support @Vyacheslav_B

[support]

@illustrious-felice It looks like your feature is prepared in a way that the computation of a log with argument zero is involved, which triggers an error. You need to handle this case, for example with a try/except clause.

[illustrious.felice]

@support Thank you so much. I have resolved this error