Dataset Versions

v3

2023-03-23 11:51am

Generated on Mar 23, 2023

Dataset Split

Train Set 96%
183Images
Valid Set 4%
8Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 16% Maximum Zoom
Rotation: Between -33° and +33°
Shear: ±25° Horizontal, ±33° Vertical
Exposure: Between -25% and +25%
Noise: Up to 5% of pixels