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

Zonotope updates 1.14 #2070

Merged
merged 7 commits into from
Mar 15, 2023

Conversation

GiulioZizzo
Copy link
Collaborator

Description

The zonotope based certified trainer should contain a check as to the type of estimator being passed in. It requires a PytorchDeepZ estimator which new users may not be aware of.

We further improve the code to minimise the amount of pylint suppression and include a more informative progress bar.

Fixes #2032

Type of change

Please check all relevant options.

  • Improvement (non-breaking)
  • Bug fix (non-breaking)
  • New feature (non-breaking)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Testing

Current zonotope tests pass and results are consistent

Test Configuration:

  • OS: MacOS
  • Python version: 3.8
  • ART version or commit number: 1.13.1
  • TensorFlow / Keras / PyTorch / MXNet version: PyTorch 1.13

Checklist

  • My code follows the style guidelines of this project
  • I have performed a self-review of my own code
  • I have commented my code
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes

GiulioZizzo and others added 5 commits March 13, 2023 14:35
Signed-off-by: GiulioZizzo <giulio.zizzo@yahoo.co.uk>
Signed-off-by: GiulioZizzo <giulio.zizzo@yahoo.co.uk>
Signed-off-by: GiulioZizzo <giulio.zizzo@yahoo.co.uk>
Signed-off-by: GiulioZizzo <giulio.zizzo@yahoo.co.uk>
@codecov-commenter
Copy link

codecov-commenter commented Mar 14, 2023

Codecov Report

Merging #2070 (31d13e7) into dev_1.14.0 (587783b) will decrease coverage by 0.01%.
The diff coverage is 77.77%.

📣 This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more

Impacted file tree graph

@@              Coverage Diff               @@
##           dev_1.14.0    #2070      +/-   ##
==============================================
- Coverage       85.58%   85.58%   -0.01%     
==============================================
  Files             294      294              
  Lines           26322    26333      +11     
  Branches         4827     4829       +2     
==============================================
+ Hits            22528    22536       +8     
- Misses           2564     2565       +1     
- Partials         1230     1232       +2     
Impacted Files Coverage Δ
...s/trainer/certified_adversarial_trainer_pytorch.py 77.53% <77.27%> (-0.25%) ⬇️
art/estimators/certification/deep_z/pytorch.py 84.71% <100.00%> (-0.10%) ⬇️

@beat-buesser beat-buesser self-requested a review March 14, 2023 14:25
@beat-buesser beat-buesser self-assigned this Mar 14, 2023
@beat-buesser beat-buesser added the improvement Improve implementation label Mar 14, 2023
@beat-buesser beat-buesser added this to the ART 1.14.0 milestone Mar 14, 2023
Copy link
Collaborator

@beat-buesser beat-buesser left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @GiulioZizzo Thank you very much for your pull request! The changes look good to me.

GiulioZizzo and others added 2 commits March 14, 2023 14:57
Signed-off-by: GiulioZizzo <giulio.zizzo@yahoo.co.uk>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
improvement Improve implementation
Projects
None yet
3 participants