Dataset Versions

v3

2022-08-17 3:14pm

Generated on Aug 17, 2022

Dataset Split

Train Set 92%
240Images
Valid Set 4%
10Images
Test Set 4%
10Images

Preprocessing

Auto-Orient: Applied
Static Crop: 27-100% Horizontal Region, 0-65% Vertical Region
Resize: Stretch to 224x224

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 22% Maximum Zoom
Shear: ±17° Horizontal, ±18° Vertical
Exposure: Between -28% and +28%
Noise: Up to 1% of pixels