Dataset Versions
v10
2024-05-07 11:20pm
Generated on May 7, 2024
2473 Total Images
View All Images
Dataset Split
Train Set 76%
1872Images
Valid Set 12%
301Images
Test Set 12%
300Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Brightness: Between -17% and +17%
Exposure: Between -10% and +10%
Noise: Up to 1.48% of pixels