Skip to content
Branch: master
Go to file

Latest commit


Failed to load latest commit information.
Latest commit message
Commit time

Deep Learning Virtual Machine

Sets up a VirtualBox VM with Keras, TensorFlow and Theano installed. A Vagrant file is used to set up this VM, which runs on Ubuntu 14.04.

Getting Started

I assume you already have VirtualBox (version 5+) installed, if you don't, please download and install it.

  1. Download and install Vagrant if you haven't previously done so.
  2. Change into the deep-learning-vm directory and run vagrant up - this creates the VM.

What's Installed

  • Deep Learning,
    • Keras, 2.0.6
    • TensorFlow, 1.3.0
    • Theano, 0.8.2
  • Python, 3.5.2
    • H5py, 2.6.0
    • MXNet, 0.10.0
    • numpy, 1.11.1
    • pandas, 0.18.1
    • scipy, 0.18.1

In addition, a Jupyter notebook server is also installed. You can view it from the host's browser at http://localhost:8100. Password : password

Testing Keras

This VM comes with a few notebooks (with required datasets).

If you'd prefer the obligatory handwritten digits example,

$ vagrant ssh
$ curl -sSL | python

The script above,, trains a simple deep neural network on the MNIST dataset. If all goes well, you should see a test accuracy close to 98.40% after 20 epochs.

Testing Theano (Optional)

Create a new notebook, and key in the following

import theano

then Run. It took ~2 hours for the 2995 tests to run in the VM on my laptop.


Sets up a VM with Keras, TensorFlow, TFLearn and Theano installed




No releases published
You can’t perform that action at this time.