Dataset Versions

v4

v1

Generated on Nov 5, 2024

Dataset Split

Train Set 88%
213Images
Valid Set 8%
20Images
Test Set 4%
9Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 1px