Skip to content

Contents of the workshop "Hands-on introduction to Deep Learning with Keras and Tensorflow" I gave at PyData Amsterdam 2018

Notifications You must be signed in to change notification settings

wombatonfire/PyDataAmsterdam2018

 
 

Repository files navigation

PyDataAmsterdam2018

Contents of the workshop "Hands-on introduction to Deep Learning with Keras and Tensorflow" I gave at PyData Amsterdam 2018.

Create the conda environment

conda env create -f environment.yml

Launch jupyter notebooks from repo root folder

jupyter notebook

Audience level: Novice

Description

Deep Learning has already conquered areas such as image recognition, NLP, voice recognition, and is a must-know tool for every Data Practitioner. This tutorial for aspiring Deep Learners will consist of a quick blunt Deep Learning overview followed by a hands-on tutorial that will teach you how to get started using Keras and Tesorflow.

Abstract

Deep Learning has already conquered areas such as image recognition, NLP, voice recognition, and is a must-know tool for every Data Practitioner. This tutorial for aspiring Deep Learners will consist of a quick blunt Deep Learning overview followed by a hands-on tutorial that will teach you how to get started using Keras and Tesorflow.

This tutorial is for people that

know the fundamentals of machine learning have a worked with the PyData stack have no deep learning hands-on experience with Keras

Curriculum

Deep learning basics Deep learning tools Basics of Keras sequential API (Hands-on) Build your first convolutional neural network (Hands-on) Transfer learning, data augmetation and on-disk datasets for image classification(Hands-on)

Prerequisites

Experience with Python and jupyter notebooks Keras or Tensorflow (version >= 1.4) installed

About

Contents of the workshop "Hands-on introduction to Deep Learning with Keras and Tensorflow" I gave at PyData Amsterdam 2018

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 89.5%
  • Python 7.8%
  • CSS 2.7%