Dataset Versions

v27

2024-03-26 10:42am

Generated on Mar 26, 2024

Dataset Split

Train Set 77%
1415Images
Valid Set 12%
218Images
Test Set 11%
202Images

Preprocessing

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

Augmentations

Outputs per training example: 5
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Blur: Up to 1.5px
Noise: Up to 1.67% of pixels
Cutout: 10 boxes with 4% size each