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

Add a Downstream Validation Task #547

Open
Pale-Blue-Dot-97 opened this issue Oct 20, 2024 · 0 comments
Open

Add a Downstream Validation Task #547

Pale-Blue-Dot-97 opened this issue Oct 20, 2024 · 0 comments
Assignees
Labels
enhancement New feature or request generalise Code needs generalising

Comments

@Pale-Blue-Dot-97
Copy link
Owner

Is your feature request related to a problem? Please describe.
There is limited support currently within minerva for proper downstream validation of a model as it is being fitted. This is particularly problematic for self-supervised training as the current Weighted KNN validation is a poor test of the model's true performance.

Describe the solution you'd like
A custom task that extracts the encoder, turns its gradients off, builds a model around the encoder then trains this model on a downstream task for several epochs, then tests it with separate validation data and logs the result.

Describe alternatives you've considered
Continue to rely on the Weighted KNN.

@Pale-Blue-Dot-97 Pale-Blue-Dot-97 added enhancement New feature or request generalise Code needs generalising labels Oct 20, 2024
@Pale-Blue-Dot-97 Pale-Blue-Dot-97 self-assigned this Oct 20, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request generalise Code needs generalising
Projects
None yet
Development

When branches are created from issues, their pull requests are automatically linked.

1 participant