Dataset Versions

v4

2024-08-14 7:43pm

Generated on Aug 14, 2024

Dataset Split

Train Set 88%
1161Images
Valid Set 8%
110Images
Test Set 4%
55Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Saturation: Between -33% and +33%
Exposure: Between -10% and +10%
Blur: Up to 1.7px
Noise: Up to 0.1% of pixels