Dataset Versions

v1

2024-08-28 6:43am

Generated on Aug 28, 2024

Dataset Split

Train Set 94%
805Images
Valid Set 4%
33Images
Test Set 2%
17Images

Preprocessing

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

Augmentations

Outputs per training example: 7
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 15% Maximum Zoom
Saturation: Between -25% and +25%
Brightness: Between -13% and +13%
Exposure: Between -10% and +10%
Noise: Up to 1.84% of pixels