Dataset Versions

v2

2023-07-14 7:57pm

Generated on Jul 14, 2023

Dataset Split

Train Set 86%
405Images
Valid Set 9%
42Images
Test Set 5%
26Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Exposure: Between -5% and +5%
Blur: Up to 1px