Dataset Versions

v1

2024-05-02 5:01am

Generated on May 2, 2024

Dataset Split

Train Set 87%
1569Images
Valid Set 8%
150Images
Test Set 4%
78Images

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
Brightness: Between -44% and +44%
Exposure: Between -10% and +10%
Blur: Up to 1.7px
Noise: Up to 1.32% of pixels