Dataset Versions

v2

2023-06-28 10:23am

Generated on Jun 28, 2023

Dataset Split

Train Set 87%
207Images
Valid Set 8%
20Images
Test Set 4%
10Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Blur: Up to 2.5px