Workshop / Overview

This full-day workshop will show you how to transform big data into a TensorFlow dataset and then use Keras and TensorFlow Eager to create linear, convolutional and recurrent prediction models. We use Colab notebooks to inspect and transform the QuickDraw dataset and train and run the models.

ML knowledge is not strictly required for understanding the TensorFlow code, but we won't have time to explain ML theory during the workshop.

Workshop / Outcome

Participants will have a working skeleton for creating their own dataset to train and run models using TensorFlow.

Workshop / Difficulty

Intermediate level

Workshop / Prerequisites

  • Python programming
  • Google account (for using Colab)
  • Own Laptop with a modern browser

Track / Co-organizers

Bartek Wołowiec

Software Engineer, Google

Megan Ruthven

Software Engineer, Google

Ruslan Habalov

Security Engineer, Google

Andreas Steiner

Software Engineer, Google

AMLD EPFL 2019 / Workshops

TensorFlow Basics 2019 – Saturday

With Bartek Wołowiec, Megan Ruthven, Ruslan Habalov & Andreas Steiner

09:00-16:30 January 26

Document Digitization Challenge

With Mihai Gurban & Raquel Terrés Cristofani

09:00-16:30 January 262A

Blue Brain Nexus, a knowledge graph for data driven projects

With Mohameth François Sy, Samuel Kerrien & Huanxiang Lu

09:00-16:30 January 272BC

AMLD / Global partners