vit

road_extraction

Instance Segmentation

road_extraction Image Dataset

v3

2023-10-14 9:33am

Generated on Oct 14, 2023

Dataset Split

Train Set 80%
65Images
Valid Set 14%
11Images
Test Set 6%
5Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied

Augmentations

Outputs per training example: 2
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Blur: Up to 2.5px