Dataset Versions

v11

2024-11-18 8:46am

Generated on Nov 18, 2024

Dataset Split

Train Set 87%
897Images
Valid Set 9%
90Images
Test Set 4%
40Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical