Skip to content

Latest commit

 

History

History
44 lines (28 loc) · 1.18 KB

README.md

File metadata and controls

44 lines (28 loc) · 1.18 KB

Docker image with pytorch-CycleGAN-and-pix2pix

We provide both Dockerfile and pre-built Docker container that runs this code repo.

Prerequisite

Running pre-built Dockerfile

  • Pull the pre-built docker file
docker pull taesungp/pytorch-cyclegan-and-pix2pix
  • Start an interactive docker session. -p 8097:8097 option is needed if you want to run visdom server on the Docker container.
nvidia-docker run -it -p 8097:8097  taesungp/pytorch-cyclegan-and-pix2pix
  • Now you are in the Docker environment. Go to pytorch-CycleGAN-and-pix2pix directory and start running things.
cd /workspace/pytorch-CycleGAN-and-pix2pix
bash datasets/download_pix2pix_dataset.sh facades
python -m visdom.server &
bash scripts/train_pix2pix.sh

Running with Dockerfile

We also posted the Dockerfile that was used to generate the pre-built file. To repeat this process, download the Dockerfile in this directory and

docker build -t [target_tag] .

in the directory that contains the Dockerfile.