Skip to content

NithinV-tech/FACE-AGE-PREDICTION

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

BRIEF DESCRIPTION OF THE CODE

-->used efficient net b0 which is trained on imagenet -->used 90 % of images for training and remaining for validation -->approach used is transfer learning --> if you closely observed i am using 1st classifier layer of efficient net and using to predict the ages

parameters used -> 20 epocs -> 0.001 lr -->weight decay used is 1e-4 -->stepsize and gamma

About

Face Age prediction using Transfer learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages