Dataset Versions

v5

2024-04-19 2:28pm

Generated on Apr 19, 2024

Dataset Split

Train Set 91%
215Images
Valid Set 4%
10Images
Test Set 4%
10Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640
Grayscale: Applied

Augmentations

Outputs per training example: 5
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 24% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±13° Horizontal, ±10° Vertical
Brightness: Between -20% and +20%
Exposure: Between -12% and +12%
Blur: Up to 2.8px
Noise: Up to 0.1% of pixels