Dataset Versions

v4

2024-02-25 1:27pm

Generated on Feb 25, 2024

Dataset Split

Train Set 85%
156Images
Valid Set 9%
17Images
Test Set 6%
11Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 224x224

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 1.05% of pixels
Cutout: 6 boxes with 10% size each