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

Tune the model #6

Open
Aubert-Antoine opened this issue Apr 14, 2023 · 1 comment
Open

Tune the model #6

Aubert-Antoine opened this issue Apr 14, 2023 · 1 comment
Assignees
Labels
Coding Write some code documentation Improvements or additions to documentation

Comments

@Aubert-Antoine
Copy link
Owner

Aubert-Antoine commented Apr 14, 2023

Tune the model :

Look on the split_test_data()

  1. Regarder le shuffle
  2. Regarder le range

Dans le reseau :
Check the theory about the batch size, step per epoch and epoch.
Look on the data set creation the arg batch sitze and on thre fit funciton

Regarder les 2 fonctions et si il ne faut pas passer dans fit_gen ImageGenerator ==> split en 2 la fonction de scikit_learn

@Aubert-Antoine Aubert-Antoine added documentation Improvements or additions to documentation Coding Write some code labels Apr 14, 2023
@Aubert-Antoine Aubert-Antoine added this to the Face detection milestone Apr 14, 2023
@Aubert-Antoine
Copy link
Owner Author

Est ce que modif tel ou tel hyper param, se voit sur le print du .fit() ?
ESt ce que noter les perf / moments de overfitting / ... peut se voir ou est ce que pas

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Coding Write some code documentation Improvements or additions to documentation
Projects
Status: No status
Development

No branches or pull requests

2 participants