Dataset Versions

v2

2023-11-21 10:51pm

Generated on Nov 22, 2023

Dataset Split

Train Set 21%
9Images
Valid Set 74%
31Images
Test Set 5%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Grayscale: Apply to 25% of images
Cutout: 4 boxes with 39% size each
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Blur: Up to 2.5px
Bounding Box: Noise: Up to 5% of pixels