-
Notifications
You must be signed in to change notification settings - Fork 99
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Passing f32 data into LSTM with Axon.Loop trainer+run causes while shape mismatch error #490
Comments
Btw, looking at this, it's not advisable to use dropout after an LSTM layer. See https://arxiv.org/pdf/1512.05287.pdf This is still a bug though |
I was just copying a Kaggle solution to practice RNNs :) Thanks for the advice! |
@polvalente Looking into this, but I am not getting the error. Could you please tell me what are the shapes of time_x and time_y? Thanks! |
@krstopro I pivoted from this approach, but I believe that x and y were just rank 1 tensors. The error appears for floating point inputs, but not integer inputs IIRC |
@polvalente time_y is for sure not rank 1, as third dimension is added with The following code seems to be working for me (
So, everything seems legit, but I might need to further inspect the output shapes of LSTMs. |
I am also seeing an issue which I think has to do with my model changing to |
Facing the same issue. Manged to solve it using
|
This issue should be fixed with the new |
The text was updated successfully, but these errors were encountered: