Dataset Versions

v8

2023-11-23 12:26am

Generated on Nov 22, 2023

Dataset Split

Train Set 82%
3222Images
Valid Set 9%
353Images
Test Set 9%
351Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 3 remapped, 3 dropped

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -30% and +30%
Brightness: Between -20% and +20%
Exposure: Between -20% and +20%
Blur: Up to 3px
Noise: Up to 10% of pixels