Dataset Versions

v1

2022-10-27 12:20am

Generated on Oct 26, 2022

Dataset Split

Train Set 90%
660Images
Valid Set 6%
44Images
Test Set 4%
29Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 15% Maximum Zoom
Rotation: Between -45° and +45°
Saturation: Between -41% and +41%
Brightness: Between -25% and +25%
Blur: Up to 0.5px