Skip to content

FaceBoxes: A CPU Real-time Face Detector with High Accuracy

Notifications You must be signed in to change notification settings

AIHGF/FaceBoxes

 
 

Repository files navigation

FaceBoxes

Repository for "FaceBoxes: A CPU Real-time Face Detector with High Accuracy", implemented with Caffe, Python interface.

Result

Face Detection

The results of each procedure in FaceBoxes are contained in result folder. The final results are shown in the flowing. 2

2

Time Cost

The average time cost is 0.15s/frame. The result is generated by testing a 720P live video.

Accuracy

The accuracy in FDDB which is higher than 0.9. The model contained in as a pretrain model and improve the result

7682A80943907539316AF0E1E11F2079

How to train

Inatall caff-ssd.

A imdb dataset is necessray to train a model.

About

FaceBoxes: A CPU Real-time Face Detector with High Accuracy

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%