Dataset Versions

v6

2024-09-19 7:07am

Generated on Sep 19, 2024

Dataset Split

Train Set 88%
492Images
Valid Set 8%
46Images
Test Set 4%
24Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640
Modify Classes: 1 remapped, 2 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal
Shear: ±5° Horizontal, ±5° Vertical
Brightness: Between -5% and +5%
Exposure: Between -10% and +10%
Noise: Up to 0.26% of pixels