Dataset Versions
v6
2023-09-19 2:27am
Generated on Sep 18, 2023
2200 Total Images
View All ImagesDataset Split
Train Set 82%
1800Images
Valid Set 9%
200Images
Test Set 9%
200Images
Preprocessing
Auto-Orient: Applied
Auto-Adjust Contrast: Using Contrast Stretching
Tile: 10 rows x 10 columns
Augmentations
Outputs per training example: 3
Shear: ±30° Horizontal, ±0° Vertical
Blur: Up to 18px
Cutout: 10 boxes with 5% size each