Skip to content

Latest commit

 

History

History
61 lines (44 loc) · 1.5 KB

INSTALL.md

File metadata and controls

61 lines (44 loc) · 1.5 KB

Installation

Requirements

We use an evironment with the following specifications, packages and dependencies:

Setup Instructions

  • Create a conda environment

    conda create --name oneformer python=3.8 -y
    conda activate oneformer
  • Install packages and other dependencies.

    git clone https://github.com/SHI-Labs/OneFormer.git
    cd OneFormer
    
    # Install Pytorch
    conda install pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -c conda-forge
    
    # Install opencv (required for running the demo)
    pip3 install -U opencv-python
    
    # Install detectron2
    python tools/setup_detectron2.py
    
    # Install other dependencies
    pip3 install git+https://github.com/cocodataset/panopticapi.git
    pip3 install git+https://github.com/mcordts/cityscapesScripts.git
    pip3 install -r requirements.txt
  • Setup wandb.

    # Setup wand
    pip3 install wandb
    wandb login
  • Setup CUDA Kernel for MSDeformAttn. CUDA_HOME must be defined and points to the directory of the installed CUDA toolkit.

    # Setup MSDeformAttn
    cd oneformer/modeling/pixel_decoder/ops
    sh make.sh
    cd ../../../..