Dataset Versions
v1
2024-01-21 8:00pm
Generated on Jan 21, 2024
569 Total Images
View All ImagesDataset Split
Train Set 88%
498Images
Valid Set 8%
47Images
Test Set 4%
24Images
Preprocessing
Auto-Orient: Applied
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -45° and +45°
Brightness: Between -15% and +15%
Exposure: Between -2% and +2%
Noise: Up to 0.3% of pixels