Dataset Versions

v1

2024-04-11 12:57am

Generated on Apr 10, 2024

Dataset Split

Train Set 87%
675Images
Valid Set 8%
65Images
Test Set 4%
32Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Hue: Between -15° and +15°
Exposure: Between -10% and +10%
Cutout: 11 boxes with 5% size each