vit

Road Network

Instance Segmentation

Road Network Image Dataset

v5

2023-12-27 2:16pm

Generated on Dec 27, 2023

Dataset Split

Train Set 88%
210Images
Valid Set 8%
20Images
Test Set 4%
10Images

Preprocessing

No preprocessing steps were applied.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -10° and +10°
Grayscale: Apply to 50% of images
Exposure: Between -15% and +15%
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down
vit
ROAD-Th9U
100 images
vit
ROAD
191 images
building-detection-boxes-to-segmentations-test
350 images