QUT2022

Stromatolites onboard detector (224 labels)

Semantic Segmentation

Stromatolites onboard detector (224 labels) Image Dataset

v2

2022-09-28 6:25pm

Generated on Sep 28, 2022

Dataset Split

Train Set 88%
471Images
Valid Set 8%
45Images
Test Set 4%
22Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 512x384
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Hue: Between -35° and +35°
Saturation: Between -40% and +40%
Brightness: Between -25% and +25%
Exposure: Between -10% and +10%
Blur: Up to 0.25px