Skip to content

chore: uses detach() instead of item() on closure to keep tensor #32

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

Open
cortexmancer wants to merge 1 commit into
base: main
Choose a base branch
from
Open

chore: uses detach() instead of item() on closure to keep tensor #32

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions breaching/attacks/optimization_based_attack.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,7 @@ def _run_trial(self, rec_model, shared_data, labels, stats, trial, initial_data=
if self.cfg.optim.boxed:
candidate.data = torch.max(torch.min(candidate, (1 - self.dm) / self.ds), -self.dm / self.ds)
if objective_value < minimal_value_so_far:
minimal_value_so_far = objective_value.detach()
minimal_value_so_far = objective_value
best_candidate = candidate.detach().clone()

if iteration + 1 == self.cfg.optim.max_iterations or iteration % self.cfg.optim.callback == 0:
Expand Down Expand Up @@ -184,7 +184,7 @@ def closure():
pass

self.current_task_loss = total_task_loss # Side-effect this because of L-BFGS closure limitations :<
return total_objective
return total_objective.detach()

return closure

Expand Down