Dataset Versions

v1

2024-02-01 1:45am

Generated on Jan 31, 2024

Dataset Split

Train Set 86%
420Images
Valid Set 8%
40Images
Test Set 5%
26Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Saturation: Between -16% and +16%
Brightness: Between -14% and +14%
Blur: Up to 1.6px
Noise: Up to 1.29% of pixels
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Rotation: Between -20° and +20°