Dataset Versions

v1

2023-12-26 10:59pm

Generated on Dec 26, 2023

Dataset Split

Train Set 88%
5746Images
Valid Set 8%
520Images
Test Set 4%
283Images

Preprocessing

Auto-Orient: Applied
Static Crop: 20-80% Horizontal Region, 20-80% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Filter Null: Require at least 85% of images to contain annotations.

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Noise: Up to 5% of pixels