Dataset Versions

v1

2024-05-14 2:49pm

Generated on May 14, 2024

Dataset Split

Train Set 87%
540Images
Valid Set 9%
53Images
Test Set 4%
26Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 500x500
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Vertical
90° Rotate: Clockwise
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Saturation: Between -20% and +20%
Brightness: Between 0% and +25%
Noise: Up to 0.54% of pixels