UniqAI/gaussian-splatting
1
0
Fork 0
mirror of https://github.com/graphdeco-inria/gaussian-splatting synced 2025-05-02 11:12:09 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README.md for docker instructions

Browse Source
This commit is contained in:
Sergio Bromberg 2023-09-04 16:35:25 +09:00 committed by GitHub
parent 47d5401448
commit 0292f3c13d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -42,6 +42,13 @@ Jonathan Stephens made a fantastic step-by-step tutorial for setting up Gaussian
User [camenduru](https://github.com/camenduru) was kind enough to provide a Colab template that uses this repo's source (status: August 2023!) for quick and easy access to the method. Please check it out [here](https://github.com/camenduru/gaussian-splatting-colab). User [camenduru](https://github.com/camenduru) was kind enough to provide a Colab template that uses this repo's source (status: August 2023!) for quick and easy access to the method. Please check it out [here](https://github.com/camenduru/gaussian-splatting-colab).
## Docker
Use the Dockerfile to build a working docker image with this repository. In order to build the container succesfully make sure that:
- NVIDIA's drivers are updated in the host machine (tested with 525.125.06)
- The default-runtime for docker is set to "nvidia" in the /etc/docker/daemon.json file. See [this](https://github.com/NVIDIA/nvidia-docker/issues/1033).
- For the above to work, the [nvidia-container-toolkit](https://gitlab.com/nvidia/container-toolkit/container-toolkit) should be installed in your host (tested with version 1.14.0-rc.2).
## Cloning the Repository ## Cloning the Repository
The repository contains submodules, thus please check it out with The repository contains submodules, thus please check it out with
@ -324,6 +331,7 @@ cd SIBR_viewers
cmake -Bbuild . -DCMAKE_BUILD_TYPE=Release # add -G Ninja to build faster cmake -Bbuild . -DCMAKE_BUILD_TYPE=Release # add -G Ninja to build faster
cmake --build build -j24 --target install cmake --build build -j24 --target install
``` ```
Alternatively, you can build a docker image using the Dockerfile mentioned above.
#### Ubuntu 20.04 #### Ubuntu 20.04
Backwards compatibility with Focal Fossa is not fully tested, but building SIBR with CMake should still work after invoking Backwards compatibility with Focal Fossa is not fully tested, but building SIBR with CMake should still work after invoking