https://github.com/nikhilroxtomar/mean-iou-in-numpy-tensorflow

A function for calculating mean iou, which can be used as a keras metrics.
https://github.com/nikhilroxtomar/mean-iou-in-numpy-tensorflow

iou-calculation semantic-segmentation tensorflow

Last synced: 2 months ago
JSON representation

A function for calculating mean iou, which can be used as a keras metrics.

• Host: GitHub
• URL: https://github.com/nikhilroxtomar/mean-iou-in-numpy-tensorflow
• Owner: nikhilroxtomar
• Created: 2019-06-28T08:01:26.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-06-29T06:43:58.000Z (about 7 years ago)
• Last Synced: 2025-03-06T12:15:52.768Z (over 1 year ago)
• Topics: iou-calculation, semantic-segmentation, tensorflow
• Language: Python
• Homepage:
• Size: 82 KB
• Stars: 3
• Watchers: 0
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Mean-IOU-in-Numpy-TensorFlow

Mean Intersection-Over-Union is a common evaluation metric for semantic image segmentation, which first computes the IOU for each semantic class and then computes the average over classes. IOU is defined as follows: 

IOU = true_positive / (true_positive + false_positive + false_negative). 


The mean iou function defined in the above code can be used as a keras metrics in any semantic segmentation task.

# Result



The above ones are the ground truth masks, and below ones are the predicted masks.