timesler/facenet-pytorch

Implement alternative detection algorithms

Open

#74 ouverte le 16 avr. 2020

Voir sur GitHub
 (0 commentaires) (2 réactions) (0 assignés)Python (830 forks)batch import
help wanted

Métriques du dépôt

Stars
 (3 830 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

As highlighted in #10, the current MTCNN design is appropriate for the project while a single detection method is implemented, but with multiple, it makes more sense to separate the return of bounding boxes and confidences from the cropping of images.

Should also think about returning facial landmarks to implement face alignment following detection.

Retinaface is probably the best option to start with.

Guide contributeur