Skip to content
No description, website, or topics provided.
Python C
Branch: master
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
train added code to generate output mask image but commented it Nov 6, 2018
trained_models Initial commit Sep 24, 2018 updated readme Nov 6, 2018


Website -


Accepted at IROS. Will be published soon!!

If you use this software in your research, please cite our publications:


For instructions please refer to the README on each folder:

  • train contains tools for training the network for semantic segmentation.Use python --savedir <save_dir> --datadir <data_dir> --num-epochs <> --batch-size <> --decoder --iouVal
  • trained_models Contains the trained models used in the papers. NOTE: the pytorch version is slightly different from the torch models.


  • The dataset: Download the "leftImg8bit" for the RGB images and the "gtFine" for the labels.
  • Python 3.6: If you don't have Python3.6 in your system, I recommend installing it with Anaconda
  • PyTorch 0.2 and above: Make sure to install the Pytorch version for Python 3.6 with CUDA support (code only tested for CUDA 8.0).
  • Additional Python packages: numpy, matplotlib, Pillow, torchvision and visdom (optional for --visualize flag)

In Anaconda you can install with:

conda install numpy matplotlib torchvision Pillow
conda install -c conda-forge visdom

If you use Pip (make sure to have it configured for Python3.6) you can install with:

pip install numpy matplotlib torchvision Pillow visdom


This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which allows for personal and research use only. For a commercial license please contact the authors. You can view a license summary here:

You can’t perform that action at this time.