Dataset Versions

v4

BW version

Generated on Mar 17, 2023

Dataset Split

Train Set 82%
222Images
Valid Set 9%
24Images
Test Set 9%
24Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 227x227
Grayscale: Applied

Augmentations

Outputs per training example: 3
Flip: Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 47% Maximum Zoom
Shear: ±9° Horizontal, ±21° Vertical
Brightness: Between -38% and +38%
Exposure: Between -26% and +26%
Blur: Up to 1.75px