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

[Macleopard]

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]

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.

Loving pyfeat!

[Macleopard]

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.

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]

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]

Thank you! I'll check it out as soon as I'm back in the lab. Looking forward to that upcoming release! Kind regards, Juan

…

On Wed, Jan 3, 2024, 13:25 Luke Chang ***@***.***> wrote: 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 <#180> and #181 <#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). — Reply to this email directly, view it on GitHub <#198 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AMGB3HB6LYR7KFNKFPN7WSDYMWBBPAVCNFSM6AAAAABAWFHYP6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQNZVGYZTMNBTGY> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>