Image Colorization using TensorFlow 2 and Keras

Offered By
Coursera Project Network
In this Guided Project, you will:

Learn how to work with images in the .npy file format.

Learn how to create a custom CNN model.

Create an app to allow users to colorize black and white images using the model you trained.

Clock1 hour 30 minutes
BeginnerBeginner
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

This guided project is about image colorization using TensorFlow2 and Keras. Image colorization comes under the computer vision domain. In this project you will learn how to build a convolutional neural network(CNN) using Tensorflow2 and Keras. While you are watching me code, you will get a cloud desktop with all the required software pre-installed. This will allow you to code along with me. After all, we learn best with active, hands-on learning. Special Feature: 1) Explanation of the process of image colorization. 2) How to reshape data to fit a CNN. 3) Explanation of each layer in a CNN. 4) Create a Streamlit app to allow users to colorize a black and white image using the model you trained. Note: This project works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop

Deep LearningConvolutional Neural NetworkTensorflowStreamlitkeras

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Preprocess grayscale images.

  2. Extract colors from colorful images to provide as inputs to the model.

  3. Build the CNN with TensorFlow2 and Keras.

  4. Save the model.

  5. Load the pre-trained model in a streamlit app.

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.