https://github.com/nheidloff/visual-recognition-tensorflow-openwhisk
Visual Recognition with TensorFlow and OpenWhisk
https://github.com/nheidloff/visual-recognition-tensorflow-openwhisk
kubernetes openwhisk tensorflow
Last synced: about 1 year ago
JSON representation
Visual Recognition with TensorFlow and OpenWhisk
- Host: GitHub
- URL: https://github.com/nheidloff/visual-recognition-tensorflow-openwhisk
- Owner: nheidloff
- License: apache-2.0
- Created: 2017-11-27T09:58:32.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-03-26T06:58:25.000Z (over 8 years ago)
- Last Synced: 2025-03-28T22:51:10.989Z (over 1 year ago)
- Topics: kubernetes, openwhisk, tensorflow
- Language: CSS
- Homepage: http://visual-recognition-tensorflow.mybluemix.net/
- Size: 5.12 MB
- Stars: 5
- Watchers: 4
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Visual Recognition with TensorFlow and OpenWhisk
This [project](https://github.com/nheidloff/visual-recognition-tensorflow-openwhisk) contains a sample application which uses an extended [MobileNet](https://research.googleblog.com/2017/06/mobilenets-open-source-models-for.html) TensorFlow model to recognize different flower types. The predictions are executed by [TensorFlow](https://www.tensorflow.org/) running in an [OpenWhisk](https://www.ibm.com/cloud/functions) function.
This project is an extension of the TensorFlow tutorial [TensorFlow for Poets](https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0) which describes how to [retrain](https://www.tensorflow.org/tutorials/image_retraining) MobileNet's final layer of a neural network for new categories.
The screenshot shows the sample web application:
## Documentation
[Ansgar Schmidt](https://ansi.23-5.eu/) and I have blogged about this project:
* [Sample Application to classify Images with TensorFlow and OpenWhisk](https://heidloff.net/article/visual-recognition-tensorflow)
* [Accessing IBM Object Store from Python](https://ansi.23-5.eu/2017/11/accessing-ibm-object-store-python/)
* [Image Recognition with Tensorflow training on Kubernetes](https://ansi.23-5.eu/2017/11/image-recognition-with-tensorflow-training-on-kubernetes/)
* [Image Recognition with Tensorflow classification on OpenWhisk](https://ansi.23-5.eu/2017/11/image-recognition-tensorflow-classification-openwhisk/)
* [Visual Recognition with TensorFlow and OpenWhisk](http://heidloff.net/article/visual-recognition-tensorflow-openwhisk)
## Prerequisites
This project only contains the web application and an OpenWhisk function which provides the classify REST API. The project [VisualRecognitionWithTensorflow](https://github.com/AnsgarSchmidt/VisualRecognitionWithTensorflow) contains the code to train the model as well as the code for a Docker image to classify flowers. You also need an instance of IBM Object Storage to store the images and the models. Check out the blog entries above.
Additionally you need an IBM Cloud account and two CLIs:
* [IBM Cloud account][sign_up]
* [Cloud Foundry CLI][cloud_foundry]
* [IBM Cloud CLI](https://console.bluemix.net/docs/cli/reference/bluemix_cli/download_cli.html)
Clone the two projects:
```sh
$ git clone https://github.com/nheidloff/visual-recognition-tensorflow-openwhisk.git
$ git clone https://github.com/AnsgarSchmidt/VisualRecognitionWithTensorflow.git
$ cd visual-recognition-tensorflow-openwhisk
```
## Setup OpenWhisk Functions
In order to deploy the two OpenWhisk functions and one sequence run the following commands from the 'openwhisk-api' directory:
```sh
$ cd openwhisk-api
$ bx login -a api.ng.bluemix.net
$ bx target -o -s
$ bx plugin install Cloud-Functions -r Bluemix
$ wsk package update visualRecognition
$ wsk action create visualRecognition/tensorflow-classify --docker /tensorflow-openwhisk-classify:latest
$ npm install
$ sh ./deploy
$ wsk action create --sequence visualRecognition/classifyAPI visualRecognition/classifyImage,visualRecognition/tensorflow-classify --web raw
```
## Setup Web Application
In the [OpenWhisk web application](https://console.bluemix.net/openwhisk/manage/actions) choose your sequence and open 'Additional Details'. From there copy the URL into the clipboard. Create a new file '.env' in the 'web-app' directory. See [.env-template](.env-template) for an example. Paste the URL in this file.
From the directory 'web-app' run these commands:
```sh
$ cd web-app
$ npm install
$ npm start
```
Open the web application via [http://localhost:3000/](http://localhost:3000/).
Optionally: In order to deploy the application to the IBM Cloud change the application name in [manifest.yml](manifest.yml) to something unique and run these commands:
```sh
$ bx login -a api.ng.bluemix.net
$ bx target -o -s
$ cf push
```
Open the web application via [http://your-application-name.mybluemix.net/](http://your-application-name.mybluemix.net/).
## License
This sample code is licensed under Apache 2.0. Full license text is available in [LICENSE](LICENSE).
## Open Source @ IBM
Find more open source projects on the [IBM Github Page](http://ibm.github.io/).
[cloud_foundry]: https://github.com/cloudfoundry/cli
[sign_up]: https://console.ng.bluemix.net/registration/
[node_js]: http://nodejs.org/
[npm]: https://www.npmjs.com