Skip to content

Latest commit

 

History

History
executable file
·
38 lines (30 loc) · 1.02 KB

install.md

File metadata and controls

executable file
·
38 lines (30 loc) · 1.02 KB

Prerequisites

  • Linux
  • Python 3.6+
  • PyTorch 1.3+
  • CUDA 9.2+ (If you build PyTorch from source, CUDA 9.0 is also compatible)
  • GCC 5+
  • MMCV

Installation

We run experiments with PyTorch 1.8.0, CUDA 11.1, Python 3.7, and Ubuntu 20.04.

Use Anaconda to create conda environment:

conda create -n GE python=3.7
conda activate GE

Install PyTorch:

conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=11.1 -c pytorch -c conda-forge

Install MMCV and our toolbox:

pip install mmcv-full==1.3.13 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.8.0/index.html

git clone https://github.com/Ma-Zhuang/GEDepth.git
cd GEDepth
pip install -e .

For training, install TensorBoard:

pip install future tensorboard

More information about installation can be found in docs of MMSegmentation (see get_started.md).