Dataset Versions

v4

2024-10-02 7:37pm

Generated on Oct 2, 2024

Dataset Split

Train Set 87%
102Images
Valid Set 9%
10Images
Test Set 4%
5Images

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 -12° and +12°
Shear: ±13° Horizontal, ±10° Vertical
Hue: Between -17° and +17°
Saturation: Between -30% and +30%
Brightness: Between -21% and +21%
Blur: Up to 2.5px

Similar Projects

See More