Dataset Versions

v1

2024-08-21 11:49am

Generated on Aug 21, 2024

Dataset Split

Train Set 85%
771Images
Valid Set 10%
86Images
Test Set 5%
48Images

Preprocessing

Auto-Orient: Applied
Static Crop: 1-99% Horizontal Region, 1-99% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 1% Maximum Zoom
Rotation: Between -1° and +1°
Shear: ±1° Horizontal, ±1° Vertical
Grayscale: Apply to 1% of images
Hue: Between -1° and +1°
Saturation: Between -10% and +10%
Brightness: Between -10% and +10%
Exposure: Between -1% and +1%
Blur: Up to 0.1px
Noise: Up to 0.02% of pixels