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

New functionality -> set a label with face number while multi-face recognition #198

Open
Macleopard opened this issue Dec 15, 2023 · 4 comments

Comments

@Macleopard
Copy link

image
Hello, in example, I have a photo with two faces. Faces are highlighted in the image, but it is difficult to understand for which face certain emotions are defined. Please, add label for this

@juaninachon
Copy link

Hi! I'm running a detector.detect_video with:

Detector(face_model="retinaface",
              landmark_model="mobilefacenet",
              au_model="xgb",
              emotion_model="resmasknet",
              facepose_model="img2pose",
              identity_model="facenet",
              device="cuda")

Is there a column in the detector.to_csv that works as an identity label? Face Rect coordinates are not very useful if subjects move around.

image

Loving pyfeat!

@Macleopard
Copy link
Author

Hi! I'm running a detector.detect_video with:

Detector(face_model="retinaface",               landmark_model="mobilefacenet",               au_model="xgb",               emotion_model="resmasknet",               facepose_model="img2pose",               identity_model="facenet",               device="cuda")

Is there a column in the detector.to_csv that works as an identity label? Face Rect coordinates are not very useful if subjects move around.

image

Loving pyfeat!

No, I recognize emotions in the photo, and I need to understand on the final image who owns what emotions, sometimes from the result of PyFeat it is not clear who is feeling what emotions

@ljchang
Copy link
Member

ljchang commented Jan 3, 2024

We have recently added a new model to embed faces into a latent representation that is commonly used in identity tracking. We have added a simple clustering algorithm to try to figure out which faces are the same across frames that you might want to try playing with. However, it's important to note that this is definitely a work in progress and we haven't added this to our plots yet. Checkout PR #180 and #181. We still need to write a tutorial on how to use it, which should be in our next major release. (We are also refactoring our plots to be more aesthetically pleasing and interactive).

@juaninachon
Copy link

juaninachon commented Jan 4, 2024 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants