Dataset Versions

v5

2024-02-14 4:59pm

Generated on Feb 14, 2024

Dataset Split

Train Set 86%
66Images
Valid Set 9%
7Images
Test Set 5%
4Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 800x800

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 50% Maximum Zoom
Grayscale: Apply to 25% of images
Hue: Between -25° and +25°
Noise: Up to 1.96% of pixels
Cutout: 12 boxes with 10% size each