Dataset Versions

v25

2023-10-17 2:37pm

Generated on Oct 17, 2023

Dataset Split

Train Set 87%
1107Images
Valid Set 6%
82Images
Test Set 6%
81Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (reflect edges) in 1024x1024

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
Saturation: Between -25% and +25%
Brightness: Between 0% and +20%
Blur: Up to 0.25px
Noise: Up to 1% of pixels
Mosaic: Applied