Dataset Versions

v1

2023-07-09 8:10pm

Generated on Jul 9, 2023

Dataset Split

Train Set 88%
924Images
Valid Set 8%
84Images
Test Set 4%
44Images

Preprocessing

Auto-Orient: Applied
Static Crop: 24-75% Horizontal Region, 23-76% Vertical Region
Resize: Stretch to 640x640
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Noise: Up to 5% of pixels