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

Regression results about the RTDL models. #42

Closed
linkedlist771 opened this issue Nov 19, 2022 · 1 comment
Closed

Regression results about the RTDL models. #42

linkedlist771 opened this issue Nov 19, 2022 · 1 comment

Comments

@linkedlist771
Copy link

linkedlist771 commented Nov 19, 2022

Hi, you did a great implementation of the tab-transformer. However, when I use your example notebook to do the simple regression for the Sin(x), neither the baseline model or the FTTransformer give the good results. I have no idea about this and want to know why.

Here is the link

@Yura52
Copy link
Collaborator

Yura52 commented Nov 19, 2022

In the cell where the training happens, you have warnings that correctly point to the issue. To fix this, you have to make y_all a one-dimensional array. Namely, instead of this line:

y_all = np.sin(X_all).astype('float32').reshape(-1, 1)

you should do this:

y_all = np.sin(X_all).astype('float32').squeeze(1)

@Yura52 Yura52 closed this as completed Nov 19, 2022
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

2 participants