Dataset Versions

v1

2024-06-17 7:37pm

Generated on Jun 17, 2024

Dataset Split

Train Set 88%
36Images
Valid Set 7%
3Images
Test Set 5%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Noise: Up to 0.42% of pixels