Dataset Versions

v6

2024-08-31 4:20pm

Generated on Aug 31, 2024

Dataset Split

Train Set 83%
1322Images
Valid Set 12%
188Images
Test Set 6%
89Images

Preprocessing

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

Augmentations

Outputs per training example: 2
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 20% of images
Hue: Between -14° and +14°
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels