Dataset Versions

v5

2024-03-22 11:22am

Generated on Mar 22, 2024

Dataset Split

Train Set 88%
5475Images
Valid Set 8%
515Images
Test Set 4%
267Images

Preprocessing

Auto-Orient: Applied
Resize: Fill (with center crop) in 1080x1080

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Blur: Up to 1px
Noise: Up to 0.73% of pixels