Dataset Versions

v2

2024-08-01 6:52am

Generated on Aug 1, 2024

Dataset Split

Train Set 87%
633Images
Valid Set 8%
61Images
Test Set 4%
30Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Saturation: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels