image segmentation

Building Semantic Segmentation

Semantic Segmentation

Building Semantic Segmentation Image Dataset

v4

2023-06-09 9:27pm

Generated on Jun 9, 2023

Dataset Split

Train Set 79%
300Images
Valid Set 13%
50Images
Test Set 8%
30Images

Preprocessing

Auto-Orient: Applied
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Grayscale: Apply to 50% of images
Brightness: Between 0% and +60%
Noise: Up to 17% of pixels
Bounding Box: 90° Rotate: Clockwise
Bounding Box: Rotation: Between -45° and +45°
Bounding Box: Shear: ±30° Horizontal, ±30° Vertical