ArcticHare105 / SPIN

The offical implementation of "Lightweight Image Super-Resolution with Superpixel Token Interaction" (ICCV2023)
MIT License
81 stars 9 forks source link

solution of “CUDA”,“Ninja” #13

Open weikangqi opened 7 months ago

weikangqi commented 7 months ago

docker is all your need

  1. first pull docker image
docker pull pytorch/pytorch:1.10.0-cuda11.3-cudnn8-devel
  1. run docker container You need to configure it according to your own ???
    docker run --gpus all -it  --shm-size="32g" --name=SPIN  -v /home/???/code:/code pytorch/pytorch:1.10.0-cuda11.3-cudnn8-devel/bin/bash
  2. in the container key steps
    cd /code/SPIN
    pip install -r requirements.txt
    chmod 1777 /tmp
    apt  install ffmpeg libsm6 libxext6  -y 
    pip install Ninja
    python train.py --config ./configs/spin_light_x4.yml