Dataset Versions

v3

2024-02-24 10:52pm

Generated on Feb 24, 2024

Dataset Split

Train Set 86%
96Images
Valid Set 9%
10Images
Test Set 5%
6Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Rotation: Between -20° and +20°
Saturation: Between -50% and +50%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px