wood class identification Dataset

v1

2023-01-04 1:56am

Generated on Jan 4, 2023

Dataset Split

Train Set 87%
120Images
Valid Set 7%
10Images
Test Set 6%
8Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Bounding Box: Blur: Up to 10px