-
Using Auto Encoder
-
Currently implemented: VAE and autoencoder - Loss for AE is column wise Damage - Loss for VAE is KL divergence + L1
-
Test set meant to pass as one batch, and in last epoch, will save generated images in Experiment folder
-
Input to model is Adult data without 'sex' and 'income'
-
'sex' column in output is the original, unchanged values
-
Notifications
You must be signed in to change notification settings - Fork 0
jctaillandier/reconstructor
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Various Deep Learning architecture attempting to reconstruct user profiles sanitized through different techniques
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published