Difficulty: beginner
Estimated Time: 30 minutes

This scenario explains the classification of handwritten digits using Keras.

The environment has a Docker installation configured, running on a host called docker. Everything else required we'll launch as containers and we will access the Jupyter Notebook in the browser to complete the tutorial.

Congratulations! You've finished the tutorial.

Don’t stop now! The next scenario will only take about 10 minutes to complete.

Deepschool.io - Keras Neural Nets

Step 1 of 2

Installing Keras

We will launch a docker container with a keras image. The image is hosted on Docker hub and has already been downloaded to this environment.

Run the following commands in the Terminal:

mkdir /srv/notebooks

chmod -R 777 /srv/notebooks

docker run -d -p=6006:6006 -p=8888:8888 -v=/srv/notebooks:/srv lisaong/jupyter-keras-cpu-py3:v1

This command takes a while to run the first time, because it will download the docker image containing Keras and Jupyter. Once download is complete, the docker image will run, which launches a Jupyter notebook server.