Dataset Versions

2024-11-17 5:56pm

Generated on Nov 17, 2024

Train Set 87%

333Images

Valid Set 13%

49Images

Test Set %

0Images

Auto-Orient: Applied

Dynamic Crop: Class: Landsite

Resize: Stretch to 640x640

Auto-Adjust Contrast: Using Adaptive Equalization

Filter Null: Require at least 70% of images to contain annotations.

Outputs per training example: 3

Flip: Horizontal, Vertical

Hue: Between -15° and +15°

Saturation: Between -25% and +25%

Brightness: Between -15% and +15%

Blur: Up to 1.1px

Cutout: 3 boxes with 12% size each

Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom

Bounding Box: Rotation: Between -8° and +8°

Bounding Box: Noise: Up to 0.1% of pixels