Keras and modern convnets, on TPUs

GDG London
Wed, Apr 14, 2021, 6:00 PM (BST)

50 RSVP'ed

About this event

In this workshop, you will learn how to build, train and tune your own convolutional neural networks from scratch with Keras and Tensorflow 2. You will also look at multiple approaches from very simple transfer learning to modern convolutional architectures such as Squeezenet. It includes theoretical explanations about neural networks and is a good starting point for developers learning about deep learning.

What you'll learn

- To use Keras and Tensor Processing Units (TPUs) to build your custom models faster.

- To use the API and the TFRecord format to load training data efficiently.

- To use transfer learning instead of building your own models.

- To use Keras sequential and functional model styles.

- To build your own Keras classifier with a softmax layer and cross-entropy loss.

- To fine-tune your model with a good choice of convolutional layers.

- To explore modern convnet architecture ideas like modules, global average pooling, etc.

- To build a simple modern convnet using the Squeezenet architecture.



  • Jana Hokszova

    Jana Hokszova

    Genesys / GDG Galway

    ML Engineer

    See Bio
  • Ivelina Doynova

    Ivelina Doynova

    Software Engineer

  • Pragati Mishra

    Pragati Mishra

    GDG, Glasgow Organiser

  • Gen Ashley

    Gen Ashley

    TECH(K)NOW / GDG London



  • Renuka Kelkar

    Renuka Kelkar


    GDG Organizer

    View Profile
  • Sumith Damodaran

    Sumith Damodaran


    PM / GDG Organizer

    View Profile
  • Jai Campbell

    Jai Campbell


    Senior Architect / GDG Organizer

    View Profile
  • Chris Bouloumpasis

    Chris Bouloumpasis

    GDG Organizer

    View Profile
  • Goran Minov

    Goran Minov


    GDG Organizer

    View Profile
  • Pranav Nagarajan

    Pranav Nagarajan

    Second Year Electronic Engineering student

    Pursuing Bachelors in Electronic Engineering

    View Profile