Dataset Versions

v4

2023-09-06 2:50am

Generated on Sep 5, 2023

Dataset Split

Train Set 81%
57Images
Valid Set 10%
7Images
Test Set 9%
6Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 43% Maximum Zoom
Rotation: Between -24° and +24°
Shear: ±31° Horizontal, ±36° Vertical
Grayscale: Apply to 100% of images
Hue: Between -25° and +25°
Saturation: Between -28% and +28%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 10% of pixels
Cutout: 4 boxes with 5% size each
Mosaic: Applied