Skip to content

Deep learning models for semantic segmentation in TensorFlow.

License

Notifications You must be signed in to change notification settings

willook/semantic-segmentation-zoo

 
 

Repository files navigation

Semantic Segmentation Zoo

This repository provides various models for semantic segmentation. The goal is to compare the various semantic segmentation models and make it easier to implement new model. Complete with the following:

  • Training and testing modes
  • Data augmentation
  • Several state-of-the-art models. Easily plug and play with different models
  • Able to use any dataset
  • Evaluation including precision, recall, f1 score, average accuracy, per-class accuracy, and mean IoU
  • Plotting of loss function and accuracy over epochs

Getting Started

This project has the following dependencies:

  • Numpy sudo pip install numpy
  • OpenCV Python sudo apt-get install python-opencv
  • TensorFlow sudo pip install --upgrade tensorflow-gpu

Then you can simply run train.py. Default dataset is CamVid. See usage documentation for more details.

Contributing

Contributions are always welcome. Any kind of contribution, such as writing a unit test, documentation, bug fix, is helpful.

Fo more detail, see the contributing documentation.

License

All code is available to you under the Apache License 2.0.

Copyright the maintainers.

About

Deep learning models for semantic segmentation in TensorFlow.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%