Dataset Versions

v5

2024-11-06 2:21pm

Generated on Nov 6, 2024

Dataset Split

Train Set 82%
180Images
Valid Set 11%
25Images
Test Set 7%
15Images

Preprocessing

Auto-Orient: Applied
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 1px