Dataset Versions

v1

model1

Generated on Nov 3, 2021

Dataset Split

Train Set 92%
4764Images
Valid Set 4%
198Images
Test Set 4%
198Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -17° and +17°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Noise: Up to 5% of pixels