Dataset Versions

v22

2024-01-26 4:12pm

Generated on Jan 26, 2024

Dataset Split

Train Set 74%
1295Images
Valid Set 16%
274Images
Test Set 10%
170Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 5
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -21° and +21°
Saturation: Between -32% and +32%
Brightness: Between -24% and +24%
Exposure: Between -15% and +15%
Blur: Up to 1.5px
Noise: Up to 1.67% of pixels