Dataset Versions

v9

2024-04-27 3:50pm

Generated on Apr 27, 2024

Dataset Split

Train Set 82%
1686Images
Valid Set 9%
187Images
Test Set 9%
187Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 224x224

Augmentations

Outputs per training example: 3
Flip: Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 35% Maximum Zoom
Rotation: Between -30° and +30°
Brightness: Between -30% and +30%
Blur: Up to 3.5px
Noise: Up to 3.5% of pixels