long-front-down-path Dataset

v4

2024-09-24 9:05am

Generated on Sep 24, 2024

Dataset Split

Train Set 82%
2880Images
Valid Set 9%
320Images
Test Set 9%
320Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 50-100% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -15° and +15°
Saturation: Between -33% and +33%
Brightness: Between -20% and +20%
Exposure: Between -5% and +5%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels