Dataset Versions

v4

2024-05-24 5:22pm

Generated on May 24, 2024

Dataset Split

Train Set 95%
942Images
Valid Set 3%
26Images
Test Set 2%
20Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Cutout: 3 boxes with 10% size each