Skip to content
GitLab

Added callbacks and validation_data suppport to DeepSVDD

Open madriss requested to merge github/fork/madriss/development into development

All Submissions Basics:

  • Have you followed the guidelines in our Contributing document?
  • Have you checked to ensure there aren't other open Pull Requests for the same update/change?
  • Have you checked all Issues to tie the PR to a specific one?

All Submissions Cores:

  • Have you added an explanation of what your changes do and why you'd like us to include them?
  • Have you written new tests for your core changes, as applicable?
  • Have you successfully ran tests with your changes locally?
  • Does your submission pass tests, including CircleCI, Travis CI, and AppVeyor?
  • Does your submission have appropriate code coverage? The cutoff threshold is 95% by Coversall.

This PR aims to help users have more control with the training of the SVDD. Now tensorflow.keras callbacks can be used during SVDD training. I have also added the possibility to use the validation_data argument when fitting the svdd, this can be especially usefull for overcoming overfitting with the use of the EarlyStopping Callback.