Skip to content

Commit e6b33df

Browse files
committed
Fixed typos in comments.
1 parent 283deef commit e6b33df

File tree

1 file changed

+5
-5
lines changed

1 file changed

+5
-5
lines changed

research/gam/gam/trainer/trainer_cotrain.py

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -355,11 +355,11 @@ def _select_samples_to_label(self, data, trainer_cls, session):
355355
assign to each of the selected nodes.
356356
"""
357357
# Select the candidate samples for self-labeling, and make predictions.
358-
# Remove the validation and test samples from the unlabeled data, if there,
359-
# to avoid self-labeling them. We could potentially leave the test edges
360-
# but once a node self-labeled, is label is fixed for the remaining
361-
# co-train iterations, and would not take advantage of the improved
362-
# versions of the model.
358+
# We remove the validation and test samples from the unlabeled data,
359+
# to avoid self-labeling them. We could potentially allow them to be
360+
# self-labeled, but once a node is self-labeled its label is fixed for
361+
# the remaining co-train iterations, so it would not take advantage
362+
# of the improved versions of the model.
363363
indices_unlabeled = data.get_indices_unlabeled()
364364
eval_ind = set(data.get_indices_val()) | set(data.get_indices_test())
365365
indices_unlabeled = np.asarray(

0 commit comments

Comments
 (0)