Dataset Versions

v1

2023-11-18 1:36am

Generated on Nov 17, 2023

Dataset Split

Train Set 93%
117Images
Valid Set 3%
4Images
Test Set 4%
5Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 4% Minimum Zoom, 22% Maximum Zoom
Rotation: Between -21° and +21°
Grayscale: Apply to 44% of images
Brightness: Between -47% and +47%
Blur: Up to 4px
Cutout: 13 boxes with 10% size each