Dataset Versions

v1

2024-10-31 5:07am

Generated on Oct 31, 2024

Dataset Split

Train Set 92%
9336Images
Valid Set 5%
534Images
Test Set 3%
267Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -15° and +15°
Saturation: Between -10% and +10%
Brightness: Between -10% and +10%
Noise: Up to 0.5% of pixels