Dataset Versions

v2

real fake face augment 2

Generated on May 16, 2022

Dataset Split

Train Set 100%
36738Images
Valid Set %
0Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 256x256
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 3 rows x 3 columns

Augmentations

Outputs per training example: 2
Grayscale: Apply to 100% of images
Hue: Between -180° and +180°
Saturation: Between -99% and +99%
Brightness: Between -99% and +99%
Exposure: Between -99% and +99%