Main

Demo-LUX

Instance Segmentation

Demo-LUX Image Dataset

v1

2023-10-01 11:09pm

Generated on Oct 1, 2023

Dataset Split

Train Set 88%
78Images
Valid Set 8%
7Images
Test Set 4%
4Images

Preprocessing

Resize: Fit (black edges) in 1280x1280

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 56% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Cutout: 3 boxes with 10% size each
Mosaic: Applied