Skip to content

adds code for safe return in case of no impostors for lmnn #36

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

Merged
merged 2 commits into from
Sep 29, 2016
Merged
Changes from all commits
Commits
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
6 changes: 6 additions & 0 deletions metric_learn/lmnn.py
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,9 @@ def fit(self, X, labels):

target_neighbors = self._select_targets()
impostors = self._find_impostors(target_neighbors[:,-1])
if len(impostors) == 0:
# L has already been initialized to an identity matrix of requisite shape
return

# sum outer products
dfG = _sum_outer_products(self.X, target_neighbors.flatten(),
Expand Down Expand Up @@ -203,6 +206,9 @@ def _find_impostors(self, furthest_neighbors):
tmp = np.ravel_multi_index((i,j), shape)
i,j = np.unravel_index(np.unique(tmp), shape)
impostors.append(np.vstack((in_inds[j], out_inds[i])))
if len(impostors) == 0:
# No impostors detected
return impostors
return np.hstack(impostors)


Expand Down