Dataset Versions

v1

2024-01-22 5-47pm

Generated on Jan 22, 2024

Dataset Split

Train Set 92%
699Images
Valid Set 6%
42Images
Test Set 3%
21Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 15% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Blur: Up to 2.5px