Dataset Versions

v4

2024-01-27 4:54pm

Generated on Jan 27, 2024

Dataset Split

Train Set 96%
1652Images
Valid Set 3%
52Images
Test Set 1%
24Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1280x1280
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 7
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Rotation: Between -25° and +25°
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -25° and +25°
Saturation: Between -30% and +30%
Brightness: Between -20% and +20%
Exposure: Between -15% and +15%
Blur: Up to 1.5px
Noise: Up to 1% of pixels