Dataset Versions

v39

2023-10-22 2:44pm

Generated on Oct 22, 2023

Dataset Split

Train Set 90%
1209Images
Valid Set 6%
80Images
Test Set 4%
53Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (reflect edges) in 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Shear: ±5° Horizontal, ±5° Vertical
Grayscale: Apply to 5% of images
Brightness: Between 0% and +25%
Exposure: Between -15% and +15%
Noise: Up to 1% of pixels
Mosaic: Applied