Skip to content

Keras with tensor flow backed, used for facial landmarking. We use android studio to load the model onto mobile device using opencv to detect faces and the trained networks to landmark.

License

connahKendrickMMU/KerasLandmarkingToAndroid

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

KerasLandmarkingToAndroid

Keras with tensor flow backed, used for facial landmarking. We use android studio to load the model onto mobile device using opencv to detect faces and the trained networks to landmark.

The code to run the model on a android device can be found at: https://www.dropbox.com/s/b71grh4ec2hrgbj/AppFinal.zip?dl=0 If you want to run your own model on the device you need to:

  • change the input/ output layers to match
  • adjust the program to work with the image size you want
  • adjust so it draws the correct amount of landmarks

About

Keras with tensor flow backed, used for facial landmarking. We use android studio to load the model onto mobile device using opencv to detect faces and the trained networks to landmark.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages