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.

Sign up for GitHub

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

Jump to bottom

Fix normalisation of y in BikeDataset #437

Open
rg936672 opened this issue Oct 11, 2024 · 0 comments
Open

Fix normalisation of y in BikeDataset #437

rg936672 opened this issue Oct 11, 2024 · 0 comments

Comments

@rg936672
Copy link
Contributor

rg936672 commented Oct 11, 2024 •
edited by tp832944
Loading

What's the issue?

Currently (in #295) BikeDataset normalises its y-values on initialisation as y /= y.mean(). Investigate whether this is correct - should we instead use y = (y - y.mean()) / y_std), or should we not be normalising at all and instead using the @NormaliseY decorator?

Check not using a non-zero constant mean.
@rg936672 rg936672 added the new Something yet to be discussed by development team label Oct 11, 2024
@tp832944 tp832944 changed the title Investigate normalisation of y in BikeDataset Fix normalisation of y in BikeDataset Oct 16, 2024
@tp832944 tp832944 removed the new Something yet to be discussed by development team label Oct 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@tp832944 @rg936672