https://github.com/sub-mod/inception-app
UI for tensorflow inception-app
https://github.com/sub-mod/inception-app
Last synced: 5 months ago
JSON representation
UI for tensorflow inception-app
- Host: GitHub
- URL: https://github.com/sub-mod/inception-app
- Owner: sub-mod
- Created: 2017-10-04T20:46:25.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-11-02T17:35:52.000Z (over 8 years ago)
- Last Synced: 2025-04-11T00:27:27.681Z (about 1 year ago)
- Language: HTML
- Homepage:
- Size: 5.86 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# install
$ pip install -r requirements.txt
$ python main.py
# dockerbuild
docker build -t submod/inception-app -f Dockerfile .
# deployment
1. Ensure that you are connected to an OpenShift project
```
oc new-project test
```
2. Create the template for inception web application.
```
oc create -f https://raw.githubusercontent.com/sub-mod/inception-app/master/template.json
```
3. Create the template for tensorflow serving endpoints.
```
oc create -f https://raw.githubusercontent.com/sub-mod/mnist-models/master/template.json
```
4. Launch tensorflow serving s2i build for the tensorflow models.We need to create a prediction
endpoints with inception model.
```
oc new-app --template=tensorflow-server --param=APPLICATION_NAME=tf-inception \
--param=MODEL_IMAGE=submod/inception-model \
--param=IMAGE_MODEL_PATH=/models/inception/1/ \
--param=MODEL_NAME=inception \
--param=MODEL_PATH=1
```
5. Launch the inception web application.
```
oc new-app --template=inceptionapp --param=APPLICATION_NAME=inception-app --param=PREDICTION_SERVICE1=tf-inception
```