Dataset Versions

v9

2024-09-03 6:22pm

Generated on Sep 3, 2024

Dataset Split

Train Set 88%
366Images
Valid Set 4%
15Images
Test Set 8%
35Images

Preprocessing

Auto-Adjust Contrast: Using Contrast Stretching
Modify Classes: 557 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -5° and +5°
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Noise: Up to 0.1% of pixels