Dataset Versions

v1

2024-12-11 3:14am

Generated on Dec 11, 2024

Dataset Split

Train Set 88%
672Images
Valid Set 8%
60Images
Test Set 4%
32Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 27% Maximum Zoom
Rotation: Between -45° and +45°
Grayscale: Apply to 15% of images
Brightness: Between -20% and +20%
Blur: Up to 2px
Noise: Up to 0.3% of pixels