Dataset Versions

v3

2023-11-03 4:52pm

Generated on Nov 3, 2023

Dataset Split

Train Set 90%
120Images
Valid Set 7%
9Images
Test Set 3%
4Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 29% Maximum Zoom
Rotation: Between -45° and +45°
Grayscale: Apply to 10% of images
Brightness: Between -32% and +32%
Noise: Up to 5% of pixels
Cutout: 3 boxes with 17% size each