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

Detection code bug #12

Open
roiaddi opened this issue Nov 9, 2016 · 0 comments
Open

Detection code bug #12

roiaddi opened this issue Nov 9, 2016 · 0 comments

Comments

@roiaddi
Copy link

roiaddi commented Nov 9, 2016

Hi there,
At yolo_main.py line 47 there is a bug:
classes_num_filtered = np.argmax(filter_mat_probs,axis=3)[filter_mat_boxes[0],filter_mat_boxes[1],filter_mat_boxes[2]]
should be
classes_num_filtered = np.argmax(probs,axis=3)[filter_mat_boxes[0],filter_mat_boxes[1],filter_mat_boxes[2]]

Basically, using argmax over filter_mat_probs, which is a boolean matrix, instead of the actual probs might cause picking the wrong class when more then one is available
Banus added a commit to Banus/caffe-yolo that referenced this issue Nov 26, 2016
@Banus
support CoCo classes, autodetect num_boxes, fix RGB order in input
3a53156 
The 'yolo_detect' module now supports CoCo classes by passing the
'--yolo' option and the number of boxes per region is now detected
automatically.
Set detection threshold to 0.25 (Darknet default).
Removed RGB->BGR conversion because Yolo uses RGB
(xingwangsfu/pull/14) and fix bug in detection
(xingwangsfu/issues/12)
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

No branches or pull requests
1 participant
@roiaddi