Dataset Versions

v2

2024-01-12 5:58pm

Generated on Jan 12, 2024

Dataset Split

Train Set 90%
1572Images
Valid Set 6%
106Images
Test Set 4%
70Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (reflect edges) in 540x540

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -13% and +13%
Blur: Up to 3px
Noise: Up to 0.1% of pixels