Dataset Versions

v2

2024-11-28 7:48pm

Generated on Nov 28, 2024

Dataset Split

Train Set 88%
207Images
Valid Set 8%
19Images
Test Set 4%
10Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-80% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -16° and +16°
Shear: ±10° Horizontal, ±14° Vertical
Blur: Up to 5.3px
Noise: Up to 2.76% of pixels
Mosaic: Applied
Bounding Box: Exposure: Between -60% and +60%