Dataset Versions

v2

Model - Histogram Equalizer

Generated on Mar 28, 2024

Dataset Split

Train Set 94%
1511Images
Valid Set 4%
62Images
Test Set 2%
31Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 480x480
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 7
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Brightness: Between -15% and +15%