Skip to content
Tensorflow turorial for Machine Learning Summer School 2018 in Algiers
Jupyter Notebook Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Tenssorflow tutorial for MLSS Algiers

This tutorial teaches the main concepts of tensorflow, necessary to extend and develop new machine learning models and algorithms. The tutorial is split into 4 parts.

  • Part 1 introduces the basics or mechanics of tensorflow
  • In part 2, you will implement our first Machine Learning model and training algorithm with the low-level tf API.
  • In part 3, we introduce very practical and useful high-level APIs to facilitate implementation and debugging.
  • In part 4, you will adapt your model from classification to a regression problem.


We only need tensorflow, numpy, matplotlib, and jupyter notebook, preferably with python3. In this tutorial, we work with simple models and toy data, so we don't need GPU support.

Install requirements

  • Install python3 and pip
  • Recommended: virtualenv with virtualenvwrapper (to create isolated environment with python packages for this tutorial).
    • sudo pip install virtualenv virtualenvwrapper

    • add the following lines to your ~/.bashrc or ~/.zshrc or ~/.bash_profile (depends what you are using)

      export WORKON_HOME=$HOME/.virtualenvs
      export VIRTUALENVWRAPPER_PYTHON=/usr/local/bin/python3
      export VIRTUALENVWRAPPER_VIRTUALENV=/usr/local/bin/virtualenv
      export VIRTUALENVWRAPPER_VIRTUALENV_ARGS='--no-site-packages'
    • mkvirtualenv tf_tutorial --python=python3

    • workon tf_tutorial

  • pip install matplotlib numpy tensorflow jupyter notebook

Alternative - Execute on google colab:

You can run your code on some google machines for free.

Go to and sign in with your google account (you need one to use colab)

File --> open notebook -->

You can’t perform that action at this time.