Dataset Versions

v20

2024-06-24 12:16pm

Generated on Jun 24, 2024

Dataset Split

Train Set 94%
4530Images
Valid Set 6%
266Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 1 dropped

Augmentations

Outputs per training example: 3
Rotation: Between -5° and +5°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -12% and +12%
Exposure: Between -15% and +15%
Noise: Up to 0.22% of pixels