Dataset Versions
Versions
v1
2023-04-02 11:43am
Generated on Apr 2, 2023
297 Total Images
View All ImagesDataset Split
Train Set 58%
171Images
Valid Set 21%
63Images
Test Set 21%
63Images
Preprocessing
Auto-Orient: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Blur: Up to 3px
Noise: Up to 3% of pixels