Dataset Versions
v2
2024-05-17 6:26pm
Generated on May 17, 2024
467 Total Images
View All ImagesDataset Split
Train Set 93%
432Images
Valid Set 4%
18Images
Test Set 4%
17Images
Preprocessing
Auto-Orient: Applied
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 40% Maximum Zoom
Saturation: Between -30% and +30%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 4px