Dataset Versions

v1

2024-09-03 7:52am

Generated on Sep 3, 2024

Dataset Split

Train Set 92%
12888Images
Valid Set 4%
539Images
Test Set 4%
538Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 224x224
Modify Classes: 0 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -14° and +14°
Saturation: Between -22% and +22%
Brightness: Between -23% and +23%
Noise: Up to 1.56% of pixels