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 tf.data.Dataset 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.
CGG / GDG London
A Self-taught Machine Learning Engineer passionate about helping and teaching junior developers getting a great start in their careers. With over 4 years of experience designing, developing, and deploying state-of-the-art solutions to real world applications. With a highly diverse educational background and cultural experiences, excels at connecting with audiences of different knowledge sets
Genesys / GDG Galway
GDG, Glasgow Organiser
TECH(K)NOW / GDG London
Jana is a recent MSc in Software Design and Development NUI Galway graduate, having previously studied law there. This has led her to a machine learning intern position at Genesys, where she is learning both about the trade and what Diversity, Equity and Inclusion mean. She likes languages, including NLP, and talking about cats and running.
PM / GDG Organizer
Senior Architect / GDG Organizer
Second Year Electronic Engineering student
Pursuing Bachelors in Electronic Engineering