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 hyperparameter tuning to episode 3 #351

Closed
2 tasks
svenvanderburg opened this issue Jun 27, 2023 · 1 comment · Fixed by #437
Closed
2 tasks

Add hyperparameter tuning to episode 3 #351

svenvanderburg opened this issue Jun 27, 2023 · 1 comment · Fixed by #437
Assignees
Labels
Episode 3 Issue related to episode 3 lesson-dev-sprint

Comments

@svenvanderburg
Copy link
Collaborator

svenvanderburg commented Jun 27, 2023

Add explanation of hyperparamter tuning to episode 3

In this section: https://carpentries-incubator.github.io/deep-learning-intro/03-monitor-the-model/index.html#counteract-model-overfitting we are actually doing hyperparamter tuning (we are changing a hyperparameter). It is only a small extra step to do this within a for-loop.

You can get inspiration from @qualiaMachine 's script here: https://colab.research.google.com/drive/1B_F5ik6P9hfbKT2pzfMgsvFeF99_Uy9V?usp=sharing

This issue resulted from discussions in #348

@svenvanderburg
Copy link
Collaborator Author

I just realized we already have something like this in the final exercise related to dropout: https://carpentries-incubator.github.io/deep-learning-intro/04-advanced-layer-types/index.html#vary-dropout-rate We can slightly build that out further by adding an infobox on grid search.

@dsmits dsmits changed the title Add hyperparamter tuning to episode 3 Add hyperparameter tuning to episode 3 Aug 15, 2023
@svenvanderburg svenvanderburg self-assigned this Jan 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Episode 3 Issue related to episode 3 lesson-dev-sprint
Development

Successfully merging a pull request may close this issue.

1 participant