Skip to content

laurauzcategui/devfest_tensorflow_workshop

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

DevFest Dublin 2019 - Tensorflow + Keras Workshop

author: @laura_uzcategui
credits to: Laurence Moroney, borrowed images and functions from his Tensorflow in Practice course.

On this workshop you will learn a bit more about Machine Learning in general and you will build a model that will help you grasp the following:

The workshop is divided in 2 sections, one for tackling the basics and to get you started in tensorflow and keras and the second part where we will be building a Convolutional Neural Net to build an image classifier

Part I

  1. Basics of Tensorflow and Keras
  2. How to build a model
  3. What are Optimizer and Loss functions and why you need them?
  4. You will train a Model and get predictions

Part II

  1. Preprocessing your data
    1. Obtain your data
    2. Load your data using image generator
    3. Explore your data
  2. Image classification and Neural Networks
    1. Build a model
    2. Configure
    3. Train your model
    4. Test it :)

Bonus points: If we have time, we will go through an explanation of Data Augmentation

Note: The following notebooks have functionality that only works in Google Colab. If you would like to make it work locally you might need to remove this functions.

Solutions to the notebooks are here:

  • Part I - Basic Keras Model: solution
  • Part II - Image Classification and Neural Nets: solution