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