Skip to content

Latest commit

 

History

History
42 lines (26 loc) · 866 Bytes

install.md

File metadata and controls

42 lines (26 loc) · 866 Bytes
Raw

Installation

We provide some advice for installation all dependencies with conda.

Prepare environment

  1. create a conda environement
conda create -n SiT python=3.7
  1. activate the environment
conda activate SiT
  1. install pytorch dependencies

Assuming GPU support, please check your CUDA version and select the appropriate installation command from PyTorch. This codebase works also for CPU only.

For CUDA 11.3 PyTorch version:

conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch -c nvidia
  1. install requierements
conda install -c conda-forge --file requirements.txt
  1. (Optional) Extra librairies

If you wish to use warm-up scheduler, you will need to pip install the following:

pip install git+https://github.com/ildoonet/pytorch-gradual-warmup-lr.git