Dataset Versions

v3

2022-10-23 8:39pm

Generated on Oct 23, 2022

Dataset Split

Train Set 89%
1280Images
Valid Set 6%
80Images
Test Set 6%
80Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 224x224

Augmentations

Outputs per training example: 2
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Noise: Up to 5% of pixels