Skip to content

Latest commit

 

History

History
57 lines (38 loc) · 1.84 KB

INSTALL.md

File metadata and controls

57 lines (38 loc) · 1.84 KB

Installation

The code was tested on Ubuntu 16.04, with Anaconda Python 3.6, CUDA 10.0, and PyTorch v1.0. It should be compatible with PyTorch <=1.4 and python >=0.4 (you will need to switch DCNv2 version for PyTorch <1.0). After installing Anaconda:

  1. [Optional but highly recommended] create a new conda environment.

    conda create --name CenterTrack python=3.6
    

    And activate the environment.

    conda activate CenterTrack
    
  2. Install PyTorch:

    conda install pytorch torchvision -c pytorch
    
  3. Install COCOAPI:

    pip install cython; pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
    
  4. Clone this repo:

    CenterTrack_ROOT=/path/to/clone/CenterTrack
    git clone --recursive https://github.com/xingyizhou/CenterTrack $CenterTrack_ROOT
    

    You can manually install the submodules if you forget --recursive.

  5. Install the requirements

    pip install -r requirements.txt
    
  6. Compile deformable convolutional (from DCNv2).

    cd $CenterTrack_ROOT/src/lib/model/networks/
    # git clone https://github.com/CharlesShang/DCNv2/ # clone if it is not automatically downloaded by `--recursive`.
    cd DCNv2
    ./make.sh
    
  7. Download pertained models for monocular 3D tracking, 80-category tracking, or pose tracking and move them to $CenterTrack_ROOT/models/. More models can be found in Model zoo.