Skip to content

The implementation of the first generation DeepID

License

Notifications You must be signed in to change notification settings

SihabSahariar/DeepID

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DeepID implementation

Reference: Deep Learning Face Representation from Predicting 10,000 Classes

DeepID Network

DeepID_Network

DeepID Node Inner Structure

DeepID_Inner_Structure

Results

  • Accuracy Accuracy
  • Loss Loss

Experiments

Best val accuracy: 99.39%

Best test accuracy: 97.05%

How to run

  • Download YoutubeFaces
  • Data preprocessing
    • run 'python crop.py', crop images and save to disk
    • run 'python split.py', split train_set, valid_set and test_set
    • run 'python convert_images_to_tfrecords.py', convert all datasets to tfrecord format
  • Training
    • run 'python train.py'
  • Testing
    • run 'python test.py'

About

The implementation of the first generation DeepID

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • Python 100.0%