-
-
Notifications
You must be signed in to change notification settings - Fork 2.3k
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
[FEATURE]: adding yolov11 into face detection portfolio #1397
Conversation
what do you mean as |
as i know, yolo is a face detector model. does it have a face recognition model as well? |
When you add a facial recognition model, you must add its pre-tuned threshold here: https://github.com/serengil/deepface/blob/master/deepface/modules/verification.py#L409 Again, AFAIK yolo is a face detection model not facial recognition. |
according to ultralytics documentation (https://docs.ultralytics.com/modes/predict/#inference-arguments) the predict method is accepting the embed parameter that "Specifies the layers from which to extract feature vectors or embeddings. Useful for downstream tasks like clustering or similarity search." |
yolo-facev8 is detecting eyes through keypoints, while for v11 keypoints are always None |
then, would you please add this information as a comment in yolo.py |
…ading in terms of documentaion. In the end not suitable for recognition at all. Removed YoloFacialRecognition
Failed at linting step
Ref: https://github.com/serengil/deepface/actions/runs/12260412979/job/34205503644?pr=1397 |
@nriviera will merge this to main when you resolve linting issues |
Thank you for your contribution |
Tickets
feature request: #1392
What has been done
This PR introduces YOLOv11[s,n,m]-face as face detector and face embedding generation
Unexpectedly yolo-facev11 is not generating any keypoint