Dataset Versions

2024-05-14 1:29pm

Generated on May 14, 2024

Train Set 87%

60Images

Valid Set 9%

6Images

Test Set 4%

3Images

Auto-Orient: Applied

Resize: Stretch to 640x640

Outputs per training example: 3

Flip: Horizontal, Vertical

Crop: 0% Minimum Zoom, 20% Maximum Zoom

Shear: ±20° Horizontal, ±9° Vertical

Grayscale: Apply to 15% of images

Hue: Between -15° and +15°

Brightness: Between -15% and +15%

Blur: Up to 1.5px

Cutout: 3 boxes with 10% size each

Mosaic: Applied

Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down

Bounding Box: Rotation: Between -15° and +15°

Bounding Box: Brightness: Between -24% and +24%

Bounding Box: Exposure: Between -10% and +10%

Bounding Box: Noise: Up to 0.5% of pixels