https://github.com/radanalyticsio/tensorflow-serving-gpu-s2i
S2I image for running tensorflow_model_server on Openshift with GPU
https://github.com/radanalyticsio/tensorflow-serving-gpu-s2i
gpu openshift s2i tensorflow
Last synced: about 1 year ago
JSON representation
S2I image for running tensorflow_model_server on Openshift with GPU
- Host: GitHub
- URL: https://github.com/radanalyticsio/tensorflow-serving-gpu-s2i
- Owner: radanalyticsio
- Created: 2017-10-30T14:52:13.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-12-07T15:47:18.000Z (over 8 years ago)
- Last Synced: 2025-04-06T17:37:41.252Z (about 1 year ago)
- Topics: gpu, openshift, s2i, tensorflow
- Language: Shell
- Homepage:
- Size: 6.84 KB
- Stars: 3
- Watchers: 1
- Forks: 3
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Radanalytics Tensorflow Serving GPU#
This S2I image is for running on Openshift with GPU.With CUDA-9 and CuDNN-7.
This is a builder image for a tensorflow serving applications. It is
meant to be used in an openshift project with tensorflow models.
The final image will have tensorflow model installed along with `tensorflow_model_server` binary from submod/tf-server:cuda9-cudnn7-centos7, a startup script and associated
utilities to start tensorflow prediction endpoint at port `6006`.
## Integration With OpenShift
To make it easier to deploy a tensorflow serving endpoint a template for OpenShift is also included. This can be loaded into your project using:
```
oc create -f https://raw.githubusercontent.com/sub-mod/tensorflow-serving-gpu-s2i/master/template.json
```
Once loaded, select the ``tensorflow-server-gpu`` template from the web console.
The ``APPLICATION_NAME`` , ``SOURCE_REPOSITORY`` and ``SOURCE_DIRECTORY``must be specified.
OR
You can create from commandline.Just create a new application within OpenShift, pointing the S2I builder at the Git repository containing your tensorflow model files.
```
oc new-app --template=tensorflow-server-gpu \
--param=APPLICATION_NAME=tf-cnn-gpu \
--param=SOURCE_REPOSITORY=https://github.com/sub-mod/mnist-models \
--param=SOURCE_DIRECTORY=gpu/cnn
```
To have any changes to your model automatically redeployed when changes are pushed back up to your Git repository, you can use the [web hooks integration](https://docs.openshift.com/container-platform/latest/dev_guide/builds.html#webhook-triggers) of OpenShift to create a link from your Git repository hosting service back to OpenShift.
## Producing a build image ##
To produce a builder image:
$ make build
To print usage information for the builder image:
$ sudo docker run -t
To poke around inside the builder image:
$ sudo docker run -i -t
bash-4.2$ cd /opt/app-root # take a look around
To tag and push a builder image:
$ sudo make push
By default this will tag the image as `submod/tensorflow-serving-s2i-gpu`,
edit the Makefile and change `PUSH_IMAGE` to control this.
## s2i bin files ##
S2i scripts are located at `./s2i/bin`.