Dataset Versions

v9

2024-04-23 9:54am

Generated on Apr 23, 2024

Dataset Split

Train Set 86%
4707Images
Valid Set 9%
470Images
Test Set 5%
287Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Rotation: Between -12° and +12°
Hue: Between -16° and +16°
Saturation: Between -20% and +20%
Brightness: Between -16% and +16%
Blur: Up to 1px
Noise: Up to 1.25% of pixels

Similar Projects

See More