Dataset Versions

v1

2023-07-01 1:44am

Generated on Jun 30, 2023

Dataset Split

Train Set 82%
6759Images
Valid Set 9%
751Images
Test Set 9%
744Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -31° and +31°
Shear: ±11° Horizontal, ±35° Vertical
Hue: Between -85° and +85°
Saturation: Between -82% and +82%
Brightness: Between -54% and +54%
Exposure: Between -1% and +1%