Dataset Versions

2024-01-21 6:46pm

Generated on Jan 21, 2024

Train Set 80%

582Images

Valid Set 11%

80Images

Test Set 10%

70Images

Auto-Orient: Applied

Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region

Resize: Stretch to 640x640

Filter Null: Require all images to contain annotations.

Outputs per training example: 3

Flip: Horizontal, Vertical

90° Rotate: Clockwise, Counter-Clockwise, Upside Down

Shear: ±8° Horizontal, ±8° Vertical

Hue: Between -20° and +20°

Saturation: Between -20% and +20%

Brightness: Between -20% and +20%

Exposure: Between -15% and +15%

Blur: Up to 1.2px

Noise: Up to 2% of pixels