Dataset Versions

v7

2024-02-16 1:49pm

Generated on Feb 16, 2024

Dataset Split

Train Set 84%
948Images
Valid Set 10%
112Images
Test Set 6%
64Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -6° and +6°
Shear: ±5° Horizontal, ±5° Vertical
Hue: Between -15° and +15°
Saturation: Between -30% and +30%
Brightness: Between -18% and +18%
Exposure: Between -15% and +15%
Blur: Up to 0.5px
Noise: Up to 0.57% of pixels

Similar Projects

See More