Dataset Versions

v2

2024-11-27 6:44pm

Generated on Nov 27, 2024

Dataset Split

Train Set 97%
231Images
Valid Set 3%
6Images
Test Set 1%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -15° and +15°
Cutout: 9 boxes with 10% size each
Mosaic: Applied
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Crop: 0% Minimum Zoom, 16% Maximum Zoom
Bounding Box: Blur: Up to 2.5px
Bounding Box: Noise: Up to 0.1% of pixels