search

qiexing / face-landmark-localization

cnn network predict face landmarks (68 points) and head pose (3d pose, yaw,roll,pitch).
410 stars 184 forks source link

Just pose angles Model. #4

Open moaljazaery opened 8 years ago

moaljazaery commented 8 years ago

Thanks for sharing the code! very good job!

You know, dlib provides good implementation for face landmarks estimation. In order to make it faster, I want to predict only the pose (yaw,roll,pitch). So if I want to predict the pose angles only, what alterations on model do you suggest in order to make it faster.

Thanks.

qiexing commented 8 years ago

I think maybe change a lightweight network structure, and make the input size smaller.

vinnitu commented 7 years ago

Have you done this modification? very interesting