For a Linux host Robert Graves answer will work, but for Mac OS X or Windows there is more to be done because docker runs in a virtual machine.
So to begin launch the docker shell (or any shell if you are using Linux) and run the following command to launch a new TensorFlow container:
docker run -p 8888:8888 -p 6006:6006 b.gcr.io/tensorflow/tensorflow ./run_jupyter.sh
Then for Mac OS X and Windows you need to do the following only once:
- Open VirtualBox
- Click on the docker vm (mine was automatically named “default”)
- Open the settings by clicking settings
- In the network settings open the port forwarding dialog
- Click the + symbol to add another port and connect a port from your mac to the VM by filling in the dialog as shown below. In this example I chose port 8810 because I run other notebooks using port 8888.
- then open a browser and connect to http://localhost:8810 (or whichever port you set in the host port section
- Make your fancy pants machine learning app!