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

Model Face Detection Confidence Score Output or Minimum Confidence Score Threshold #8272

Open
thaddmt opened this issue May 7, 2024 · 0 comments
Assignees
Labels
comp:models type:feature New feature or request

Comments

@thaddmt
Copy link

thaddmt commented May 7, 2024

Please make sure that this is a feature request. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:feature_template

System information

  • TensorFlow.js version (you are using): @tensorflow-models/face-detection@1.0.2
  • Are you willing to contribute it (Yes/No): Yes

Describe the feature and the current behavior/state.
Currently the TFJS Face detection model doesn't allow for configuring the minimum confidence score threshold while this appears to be possible in MediaPipe itself. Previously it seems like the TFJS blazeface model returned a probability field.

Is it possible to add either of these so that we could filter out faces based on their confidence threshold or probability?

This other relevant issue tensorflow/tensorflow#62683 mentions that the media pipe short range documentation shows that a detection confidence score should be returned.

Will this change the current api? How?
Would need to add some configuration to set the minimum thresholds or change the output to return a probability.

Who will benefit with this feature?
Users of TFJS face detection

Any Other info.

@thaddmt thaddmt added the type:feature New feature or request label May 7, 2024
@gaikwadrahul8 gaikwadrahul8 self-assigned this May 8, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
comp:models type:feature New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants