Skip to main content

Image Processing with Keras in Python

Learn powerful techniques for image analysis in Python using deep learning and convolutional neural networks in Keras.

Start Course for Free
4 Hours13 Videos45 Exercises25,568 Learners
3650 XP

Create Your Free Account

GoogleLinkedInFacebook

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA. You confirm you are at least 16 years old (13 if you are an authorized Classrooms user).

Loved by learners at thousands of companies

Course Description

Deep learning methods use data to train neural network algorithms to do a variety of machine learning tasks, such as classification of different classes of objects. Convolutional neural networks are deep learning algorithms that are particularly powerful for analysis of images. This course will teach you how to construct, train and evaluate convolutional neural networks. You will also learn how to improve their ability to learn from data, and how to interpret the results of the training.

  1. 1

    Image Processing With Neural Networks

    Free

    Convolutional neural networks use the data that is represented in images to learn. In this chapter, we will probe data in images, and we will learn how to use Keras to train a neural network to classify objects that appear in images.

    Play Chapter Now
    Introducing convolutional neural networks
    50 xp
    Images as data: visualizations
    100 xp
    Images as data: changing images
    100 xp
    Classifying images
    50 xp
    Using one-hot encoding to represent images
    100 xp
    Evaluating a classifier
    100 xp
    Classification with Keras
    50 xp
    Build a neural network
    100 xp
    Compile a neural network
    100 xp
    Fitting a neural network model to clothing data
    100 xp
    Cross-validation for neural network evaluation
    100 xp
  2. 2

    Using Convolutions

    Convolutions are the fundamental building blocks of convolutional neural networks. In this chapter, you will be introducted to convolutions and learn how they operate on image data. You will also see how you incorporate convolutions into Keras neural networks.

    Play Chapter Now
    Convolutions
    50 xp
    One dimensional convolutions
    100 xp
    Image convolutions
    100 xp
    Defining image convolution kernels
    100 xp
    Implementing image convolutions in Keras
    50 xp
    Convolutional network for image classification
    100 xp
    Training a CNN to classify clothing types
    100 xp
    Evaluating a CNN with test data
    100 xp
    Tweaking your convolutions
    50 xp
    Add padding to a CNN
    100 xp
    Add strides to a convolutional network
    100 xp
    Calculate the size of convolutional layer output
    50 xp
  3. 3

    Going Deeper

    Convolutional neural networks gain a lot of power when they are constructed with multiple layers (deep networks). In this chapter, you will learn how to stack multiple convolutional layers into a deep network. You will also learn how to keep track of the number of parameters, as the network grows, and how to control this number.

    Play Chapter Now
    Going deeper
    50 xp
    Creating a deep learning network
    100 xp
    Train a deep CNN to classify clothing images
    100 xp
    What is special about a deep network?
    50 xp
    How many parameters?
    50 xp
    How many parameters in a CNN?
    50 xp
    How many parameters in a deep CNN?
    100 xp
    Pooling operations
    50 xp
    Write your own pooling operation
    100 xp
    Keras pooling layers
    100 xp
    Train a deep CNN with pooling to classify images
    100 xp
  4. 4

    Understanding and Improving Deep Convolutional Networks

    There are many ways to improve training by neural networks. In this chapter, we will focus on our ability to track how well a network is doing, and explore approaches towards improving convolutional neural networks.

    Play Chapter Now
    Tracking learning
    50 xp
    Plot the learning curves
    100 xp
    Using stored weights to predict in a test set
    100 xp
    Regularization
    50 xp
    Adding dropout to your network
    100 xp
    Add batch normalization to your network
    100 xp
    Interpreting the model
    50 xp
    Extracting a kernel from a trained network
    100 xp
    Shape of the weights
    50 xp
    Visualizing kernel responses
    100 xp
    Next steps
    50 xp

In the following tracks

Image ProcessingMachine Learning Scientist

Collaborators

Sumedh PanchadharLore DirickEunkyung Park

Prerequisites

Introduction to Deep Learning in Python
Ariel Rokem Headshot

Ariel Rokem

Senior Data Scientist, University of Washington

Ariel Rokem is a Data Scientist at the University of Washington eScience Institute. He received a PhD in neuroscience from UC Berkeley, and postdoctoral training in computational neuroimaging at Stanford. In his work, he develops data science algorithms and tools, and applies them to analysis of neural data. He is also a contributor to multiple open-source software projects in the scientific Python ecosystem.
See More

What do other learners have to say?

I've used other sites—Coursera, Udacity, things like that—but DataCamp's been the one that I've stuck with.

Devon Edwards Joseph
Lloyds Banking Group

DataCamp is the top resource I recommend for learning data science.

Louis Maiden
Harvard Business School

DataCamp is by far my favorite website to learn from.

Ronald Bowers
Decision Science Analytics, USAA