Dataset Versions

v4

2024-08-29 6:50am

Generated on Aug 29, 2024

Dataset Split

Train Set 88%
942Images
Valid Set 8%
89Images
Test Set 4%
44Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Hue: Between -17° and +17°
Saturation: Between -27% and +27%
Exposure: Between -15% and +15%
Noise: Up to 0.89% of pixels