Dataset Versions

v2

2023-04-01 10:21am

Generated on Apr 1, 2023

Dataset Split

Train Set 73%
171Images
Valid Set 26%
60Images
Test Set 1%
3Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 15% Maximum Zoom
Rotation: Between -10° and +10°
Shear: ±10° Horizontal, ±10° Vertical
Blur: Up to 1.25px
Noise: Up to 5% of pixels