Dataset Versions

v8

2024-10-29 12:03pm

Generated on Oct 29, 2024

Dataset Split

Train Set 90%
276Images
Valid Set 6%
19Images
Test Set 3%
10Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (reflect edges) in 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 4
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -15° and +15°
Exposure: Between -11% and +11%