Dataset Versions

v1

2024-03-15 2:30pm

Generated on Mar 15, 2024

Dataset Split

Train Set 88%
318Images
Valid Set 8%
30Images
Test Set 4%
15Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Hue: Between -20° and +20°
Saturation: Between -25% and +25%
Blur: Up to 1px
Noise: Up to 0.1% of pixels
Cutout: 5 boxes with 5% size each