-
Notifications
You must be signed in to change notification settings - Fork 25
Add custom inference model #51
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 custom inference model #51
Conversation
|
Successor of #48 implementing custom ML models as inference attack algorithms. |
MatteoGiomi
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks a lot @itrajanovska for this contribution, looks very good now. This feature still needs to be documented, but as discussed afk, better do it in a dedicated PR.
Thank you for your feedback @MatteoGiomi , I will merge this PR and will address the remaining comments in a separate PR. |
…ator.py; Compute risks for every group within the target column; Add an example notebook.
Create class wrappers for a KNN and the ml model; Update example inference_custom_model_example.ipynb.
Add Inference model wrappers extending InferencePredictor in inference_predictor.py; Support different number of attacks; Add tests.
487e2e3 to
fd4b88d
Compare
MatteoGiomi
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thanks for addressing my comments!
Add a custom inference model in the inference_evaluator.py;
Add Inference model wrappers extending InferencePredictor in inference_predictor.py;
Support different number of attacks;
Add tests.