Skip to content
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

Issue running example #3

Open
hcorbaz opened this issue May 3, 2024 · 3 comments
Open

Issue running example #3

hcorbaz opened this issue May 3, 2024 · 3 comments

Comments

@hcorbaz
Copy link

hcorbaz commented May 3, 2024

Hello,

This project looks really interesting, but I encountered some error while running the example. When running the file titanic_missingness_pipeline.py, this error message is happening RuntimeError: Predictions and targets are expected to have the same shape, but got torch.Size([43]) and torch.Size([177]).

Thanks a lot!

@ACoeruleus
Copy link

Hi,

thanks for bringing this up, I had the same mistake. For me the code runs when I unindent twice the lines 347-357 in 'multimodn.py' (creation of the confusion matrices).

Not sure if this is really what is needed though...

Best, AC

@imannajwa-masrun
Copy link

Hi,

thanks for bringing this up, I had the same mistake. For me the code runs when I unindent twice the lines 347-357 in 'multimodn.py' (creation of the confusion matrices).

Not sure if this is really what is needed though...

Best, AC

Had the same issue and this worked! Thank you.

@hcorbaz
Copy link
Author

hcorbaz commented May 7, 2024

Hello,

Thanks a lot for your answer! It indeed fixed the training, but the validation looks wrong: it returns 0.5 for each epoch and the plots are empty. This confusion matrix is confusing me.
Thanks again for your help!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants