Dataset Versions

v11

2024-06-22 6:07am

Generated on Jun 22, 2024

Dataset Split

Train Set 87%
1662Images
Valid Set 8%
158Images
Test Set 4%
80Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Blur: Up to 2.5px
Noise: Up to 0.5% of pixels