Dataset Versions

v5

2023-11-30 12:52am

Generated on Nov 29, 2023

Dataset Split

Train Set 93%
195Images
Valid Set 5%
10Images
Test Set 2%
5Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Hue: Between -25° and +25°
Brightness: Between -25% and +25%
Noise: Up to 5% of pixels
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom
Bounding Box: Rotation: Between -30° and +30°
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Exposure: Between -25% and +25%
Bounding Box: Blur: Up to 2.5px