Dataset Versions

v10

2024-09-12 8:58am

Generated on Sep 12, 2024

Dataset Split

Train Set 93%
2550Images
Valid Set 5%
125Images
Test Set 2%
59Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (black edges) in 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±14° Horizontal, ±14° Vertical
Grayscale: Apply to 6% of images
Hue: Between -25° and +25°
Saturation: Between -33% and +33%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 1.5px
Noise: Up to 1.57% of pixels
Bounding Box: Noise: Up to 1.54% of pixels

Similar Projects

See More