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.

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

fix problem when training yolov3 with no-valid-bbox img #1555

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
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
3 changes: 3 additions & 0 deletions gluoncv/data/pascal_voc/detection.py
Original file line number Diff line number Diff line change
Expand Up @@ -130,6 +130,9 @@ def _load_label(self, idx):
label.append([xmin, ymin, xmax, ymax, cls_id, difficult])
except AssertionError as e:
logging.warning("Invalid label at %s, %s", anno_path, e)
if not label:
# dummy invalid labels if no valid objects are found
label.append([-1, -1, -1, -1, -1, -1])
return np.array(label)

def _validate_label(self, xmin, ymin, xmax, ymax, width, height):
Expand Down
2 changes: 2 additions & 0 deletions gluoncv/model_zoo/yolo/yolo_target.py
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,8 @@ def forward(self, img, xs, anchors, offsets, gt_boxes, gt_ids, gt_mixratio=None)
for m in range(matches.shape[1]):
if valid_gts[b, m] < 1:
break
if np_gt_ids[b, m, 0] < 0: # ignore fake bbox
break
match = int(matches[b, m])
nlayer = np.nonzero(num_anchors > match)[0][0]
height = xs[nlayer].shape[2]
Expand Down