Dataset Versions

v11

2024-12-04 8:58am

Generated on Dec 4, 2024

Dataset Split

Train Set 92%
1550Images
Valid Set 5%
89Images
Test Set 3%
45Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 5
Grayscale: Apply to 15% of images
Hue: Between -22° and +22°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 1.1px
Noise: Up to 0.1% of pixels