Five-Project Series

Image Classification with AutoKeras you own this product

prerequisites
basic Python, pandas, Matplotlib, NumPy, SciPy, scikit-learn, and deep learning/Keras
skills learned
training deep learning models automatically with AutoKeras • building AutoML pipelines for image classification • designing a hyperblock for model selection
Xiaotian Han
5 weeks · 4-6 hours per week average · INTERMEDIATE

pro $24.99 per month

  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose one free eBook per month to keep
  • exclusive 50% discount on all purchases

lite $19.99 per month

  • access to all Manning books, including MEAPs!

team

5, 10 or 20 seats+ for your team - learn more


In this series of liveProjects, you’ll utilize premade machine learning components to help build an image classification AI solution. This automated approach to machine learning—called AutoML—utilizes toolkits and libraries to help streamline and automatically process different parts of the machine learning pipeline. In this series, you’ll utilize the AutoKeras toolkit from the popular Keras deep learning library. Each project in this series covers a different stage of the process of creating an image classifier, from the basics of deep learning through to customizing AutoKeras.

These projects are designed for learning purposes and are not complete, production-ready applications or solutions.

here's what's included

Project 1 Basic Deep Learning

In this liveProject, you’ll learn and apply some of the basics of deep learning in order to build the foundations of an AutoML image classifier. You’ll discover the basic deep learning models for image classification, and then experiment with tuning the hyperparameters of a convolutional neural network to improve your results.

Project 2 Basic API of AutoKeras

In this liveProject, you’ll learn how to use the Task and Functional API of Keras to build an automated deep learning model for image classification. This AutoML approach will allow you to avoid time spent selecting and tuning your deep learning algorithms. You’ll work with the detailed CIFAR dataset of animal images which is easy to access through the TensorFlow Keras API.

Project 3 Automate Data Preprocessing

In this liveProject, you’ll utilize automated machine learning tools to help the data preprocessing and feature engineering for creating an image classification model. You’ll start with the basics of data preprocessing, and then see how useful AutoML solutions can make this process quicker and easier. The rewards are big, as properly preprocessed data can dramatically improve the outcomes of a deep learning project.

Project 4 Automate Pipeline

In this liveProject, you’ll implement an AutoML pipeline using the AutoKeras functional API. You’ll make use of the built-in blocks in AutoKeras to conduct automated hyperparameter tuning and model selection for creating an image classification model. Your challenges will include customizing both a sequential AutoML pipeline, and customizing graph-structured AutoML Pipeline.

Project 5 Customize AutoKeras Blocks

In this liveProject, you’ll build an AutoKeras block for image classification to help tune a neural network and customize the search space. You’ll then combine the block you have created with other prebuilt AutoKeras blocks to put together a complete automated machine learning pipeline.

book resources

When you start each of the projects in this series, you'll get full access to the following book for 90 days.

choose your plan

team

monthly
annual
$49.99
$499.99
only $41.67 per month
  • five seats for your team
  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose another free product every time you renew
  • choose twelve free products per year
  • exclusive 50% discount on all purchases
  • Image Classification with AutoKeras project for free

project author

Xiaotian Han
Xiaotian Han is a PhD student at Texas A&M University, where he works in the field of data mining and automated machine learning. He has published several research papers related to data mining and automated machine learning and participated in an open-source package, AutoRec, which is highly based on the AutoKeras.

Prerequisites

This liveProject is for Python programmers who know the basics of deep learning. To begin this liveProject, you will need to be familiar with the following:


TOOLS
  • Basic Python
  • Basic pandas
  • Basic Matplotlib
  • Basic NumPy
  • Basic SciPy
  • Basic scikit-learn
TECHNIQUES
  • Basic deep learning/Keras
  • Basics of image data processing

features

Self-paced
You choose the schedule and decide how much time to invest as you build your project.
Project roadmap
Each project is divided into several achievable steps.
Get Help
While within the liveProject platform, get help from other participants and our expert mentors.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
book resources
Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.