Dataset Versions

v2

2023-09-25 7:37pm

Generated on Sep 25, 2023

Dataset Split

Train Set 88%
42Images
Valid Set 8%
4Images
Test Set 4%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 14% Maximum Zoom
Rotation: Between -20° and +20°
Hue: Between -31° and +31°
Saturation: Between -60% and +60%
Brightness: Between -40% and +40%
Exposure: Between -25% and +25%
Noise: Up to 5% of pixels
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Bounding Box: Brightness: Between -19% and +19%
Bounding Box: Exposure: Between -18% and +18%
Bounding Box: Noise: Up to 4% of pixels