Dataset Versions

v1

2023-01-18 10:33pm

Generated on Jan 18, 2023

Dataset Split

Train Set 83%
60Images
Valid Set 6%
4Images
Test Set 11%
8Images

Preprocessing

Auto-Orient: Applied
Static Crop: 9-48% Horizontal Region, 13-67% Vertical Region
Auto-Adjust Contrast: Using Contrast Stretching
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Saturation: Between -56% and +56%
Brightness: Between -26% and +26%
Blur: Up to 5.5px
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Bounding Box: Noise: Up to 10% of pixels

Similar Projects

See More