https://github.com/mrgloom/keras-semantic-segmentation-example

Example of semantic segmentation in Keras
https://github.com/mrgloom/keras-semantic-segmentation-example

convolutional-neural-networks deep-learning keras proof-of-concept segmentation toy-project

Last synced: about 2 months ago
JSON representation

Example of semantic segmentation in Keras

• Host: GitHub
• URL: https://github.com/mrgloom/keras-semantic-segmentation-example
• Owner: mrgloom
• Created: 2017-08-20T09:37:05.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2018-06-23T22:16:31.000Z (almost 7 years ago)
• Last Synced: 2024-10-31T23:42:29.508Z (7 months ago)
• Topics: convolutional-neural-networks, deep-learning, keras, proof-of-concept, segmentation, toy-project
• Language: Python
• Size: 46.9 KB
• Stars: 56
• Watchers: 6
• Forks: 23
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# keras-semantic-segmentation-example

Example of semantic segmentation in Keras

## Single class example:

Generated data: random ellipse with random color on random color background and with random noise added.

Result: 1st images is input image, 2nd image is ground truth mask, 3rd image is probability, 4th image is probability thresholded at 0.5.

![alt tag](https://github.com/mrgloom/keras-semantic-segmentation-example/blob/master/misc/binary_crossentropy_result_binary_segmentation.png)

## Multi-class example:

Generated data: first class is random ellipse with random color and second class is random rectangle with random color on random color background and with random noise added.

Result: 1st images is input image, 2nd image is ground truth mask, 3rd image is probability, 4th image is probability thresholded at 0.5.

![alt tag](https://github.com/mrgloom/keras-semantic-segmentation-example/blob/master/misc/binary_crossentropy_result_multilabel_segmentation.png)