Dataset Versions

v5

2024-07-12 3:28am

Generated on Jul 12, 2024

Dataset Split

Train Set 97%
462Images
Valid Set 3%
16Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -3° and +3°
Saturation: Between -22% and +22%
Brightness: Between -21% and +21%
Blur: Up to 2.1px
Noise: Up to 0.42% of pixels