face-alignment-at-3000fps icon indicating copy to clipboard operation
face-alignment-at-3000fps copied to clipboard

Published 20 hours ago • verified publisher icon freesouls

fps of testing

Open vinccccho opened this issue 8 years ago • 1 comments

hi, do you know how fast it is when testing on one image? have you analyse its fps? Thanks!

vinccccho avatar Jul 04 '16 16:07 vinccccho

I have written in README.md

  • The paper claims for 3000fps for very high frame rates for different parameters, while my implementation can achieve several hundreds frame rates. What you should be AWARE of is that we both just CALCULATE the time that predicting the landmarks, EXCLUDES the time that detecting faces.
  • If you want to use it for realtime videos, using OpenCV's face detector will achieve about 15fps, since 80% (even more time is used to get the bounding boxes of the faces in an image), so the bottleneck is the speed of face detection, not the speed of landmarks predicting. You are required to find a fast face detector(For example, libfacedetection)

the frame rate varies according to the model complexity.

freesouls avatar Jul 07 '16 04:07 freesouls