Dataset Versions

v8

2024-05-02 11:51am

Generated on May 2, 2024

Dataset Split

Train Set 93%
3735Images
Valid Set 5%
191Images
Test Set 3%
101Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 5
90° Rotate: Clockwise, Counter-Clockwise
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels