Dataset Versions

v8

2023-07-21 3:31pm

Generated on Jul 21, 2023

Dataset Split

Train Set 87%
384Images
Valid Set 9%
38Images
Test Set 4%
17Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Brightness: Between -33% and +33%
Blur: Up to 1px
Cutout: 6 boxes with 20% size each