Dataset Versions

v2

2024-06-05 10:39pm

Generated on Jun 6, 2024

Dataset Split

Train Set 88%
252Images
Valid Set 8%
24Images
Test Set 4%
12Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x360

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±20° Horizontal, ±20° Vertical
Brightness: Between -25% and +0%
Blur: Up to 1px
Noise: Up to 1.21% of pixels