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.

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

Measure CARLA detector adversarial performance wrt benign predictions #1218

Closed
lcadalzo opened this issue Dec 3, 2021 · 1 comment · Fixed by #1225
Closed

Measure CARLA detector adversarial performance wrt benign predictions #1218

lcadalzo opened this issue Dec 3, 2021 · 1 comment · Fixed by #1225

Comments

@lcadalzo
Copy link
Contributor

lcadalzo commented Dec 3, 2021

The metrics logger in carla_object_detection.py should be updated to support computation of metrics relative to the benign prediction (rather than groundtruth).

armory/armory/scenarios/carla_object_detection.py

Line 67 in a5d2c29

self.metrics_logger.update_task(y_object, y_pred_adv, adversarial=True)
can be duplicated and then changed to use self.y_pred
@lcadalzo lcadalzo mentioned this issue Dec 9, 2021
Merged
@lcadalzo lcadalzo linked a pull request Dec 9, 2021 that will close this issue
measure CARLA adversarial performance using benign predictions as labels #1225
Merged
@lcadalzo
Copy link
Contributor Author

Closing due to #1225

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

measure CARLA adversarial performance using benign predictions as labels lcadalzo/armory
1 participant
@lcadalzo