Need help with OSVOS-PyTorch?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.


PyTorch implementation of One-Shot Video Object Segmentation (OSVOS)

478 Stars 94 Forks GNU General Public License v3.0 35 Commits 2 Opened issues

Services available

Need anything else?

OSVOS: One-Shot Video Object Segmentation

Check our project page for additional information. OSVOS

This repository was ported to PyTorch 0.4.0!

OSVOS is a method that tackles the task of semi-supervised video object segmentation. It is based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Experiments on DAVIS 2016 show that OSVOS is faster than currently available techniques and improves the state of the art by a significant margin (79.8% vs 68.0%).

This PyTorch code is a posteriori implementation of OSVOS and it does not contain the boundary snapping branch. The results published in the paper were obtained using the Caffe version that can be found at OSVOS-caffe. TensorFlow implementation is also available at OSVOS-TensorFlow.


  1. Clone the OSVOS-PyTorch repository
    git clone
  2. Install - if necessary - the required dependencies:
  • Python (tested with Anaconda 2.7 and 3.6)
  • PyTorch (
    conda install pytorch torchvision -c pytorch
    - tested with PyTorch 0.4, CUDA 8.0 and 9.0)
  • Other python dependencies: numpy, scipy, matplotlib, opencv-python, graphviz.
  • Optionally, install tensorboard (
    pip install tensorboard tensorboardx
    1. Edit the paths in

Online training and testing

  1. Download the parent model (55 MB), and unzip it under
    , by running:
    cd models/
    chmod +x
    cd ..
  2. Edit in file
    the 'User defined parameters' (eg. gpu_id, etc).
  3. Run

Training the parent network (optional)

  1. All the training sequences of DAVIS 2016 are required to train the parent model, thus download them from here.
  2. Download the VGG model (55 MB) pretrained on ImageNet, and unzip it under
    , by running:
    cd models/
    chmod +x
    cd ..
  3. Place the files with the train and test sequences names in the DAVIS root folder (
  4. Edit the 'User defined parameters' (eg. gpuid) in file ``.
  5. Run
    . This step takes 20 hours to train (Titan-X Pascal).



  Title          = {One-Shot Video Object Segmentation},
  Author         = {S. Caelles and K.K. Maninis and J. Pont-Tuset and L. Leal-Taix\'e and D. Cremers and L. {Van Gool}},
  Booktitle      = {Computer Vision and Pattern Recognition (CVPR)},
  Year           = {2017}

If you encounter any problems with the code, want to report bugs, etc. please contact us at {kmaninis, scaelles}[at]vision[dot]ee[dot]ethz[dot]ch.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.