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.

Sign up for GitHub

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

Jump to bottom

Inconsistent implementation of get_random_layer_generator for Torch and TF #285

Open

aaarrti opened this issue Jul 20, 2023 · 0 comments

Labels

bug refactoring

Collaborator

aaarrti commented Jul 20, 2023

Description

Here https://github.com/understandable-machine-intelligence-lab/Quantus/blob/main/quantus/helpers/model/tf_model.py#L272 for Keras model we shuffle each layer weights.
Here https://github.com/understandable-machine-intelligence-lab/Quantus/blob/main/quantus/helpers/model/pytorch_model.py#L213 for torch model we reset module parameters (to default ones.)

Minimum acceptance criteria

Include both weight modification strategies for both framework's models.
Keep the default version uniform.

aaarrti added bug refactoring labels

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment