diff options
| author | ngimel <ngimelshein@nvidia.com> | 2017-01-25 14:30:29 -0800 |
|---|---|---|
| committer | Soumith Chintala <soumith@gmail.com> | 2017-01-25 17:30:29 -0500 |
| commit | 3c2ecc6b15d3deeabd5905849d242bbee2264eee (patch) | |
| tree | 110c810e7012781b09003459fbc12cfe05019a58 /README.md | |
| parent | aa46055274a2aad88b4c8969047d53ecac52236a (diff) | |
| download | pytorch-3c2ecc6b15d3deeabd5905849d242bbee2264eee.tar.gz pytorch-3c2ecc6b15d3deeabd5905849d242bbee2264eee.tar.bz2 pytorch-3c2ecc6b15d3deeabd5905849d242bbee2264eee.zip | |
add dockerfiles (#583)
* add dockerfiles
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 20 |
1 files changed, 20 insertions, 0 deletions
@@ -14,6 +14,7 @@ We are in an early-release Beta. Expect some adventures and rough edges. - [Installation](#installation) - [Binaries](#binaries) - [From source](#from-source) + - [Docker image](#docker-image) - [Getting Started](#getting-started) - [Communication](#communication) - [Releases and Contributing](#releases-and-contributing) @@ -169,6 +170,25 @@ pip install -r requirements.txt python setup.py install ``` +### Docker image + +Dockerfiles are supplied to build images with cuda support and cudnn v5 and cudnn v6 RC. Build them as usual +``` +docker build . -t pytorch-cudnnv5 +``` +or +``` +docker build . -t pytorch-cudnnv6 -f tools/docker/Dockerfile-v6 +``` +and run them with nvidia-docker: +``` +nvidia-docker run --rm -ti --ipc=host pytorch-cudnnv5 +``` +Please note that pytorch uses shared memory to share data between processes, so if torch multiprocessing is used (e.g. +for multithreaded data loaders) the default shared memory segment size that container runs with is not enough, and you +should increase shared memory size either with --ipc=host or --shm-size command line options to nvidia-docker run. + + ## Getting Started Three pointers to get you started: |