Dataset Versions

v3

2024-10-26 3:50am

Generated on Oct 26, 2024

Dataset Split

Train Set 88%
213Images
Valid Set 9%
22Images
Test Set 3%
8Images

Preprocessing

Auto-Orient: Applied
Dynamic Crop: Class: facade
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom
Bounding Box: Brightness: Between -15% and +15%
Bounding Box: Blur: Up to 2.5px