Creating Multi Task Models With Keras

4.6
stars

54 ratings

Offered By

2,556 already enrolled

In this Free Guided Project, you will:

Creating multi-task models with Keras

Training multi-task models with Keras

Showcase this hands-on experience in an interview

2 hours
Intermediate
No download needed
Split-screen video
English
Desktop only

In this 1 hour long guided project, you will learn to create and train multi-task, multi-output models with Keras. You will learn to use Keras' functional API to create a multi output model which will be trained to learn two different labels given the same input example. The model will have one input but two outputs. A few of the shallow layers will be shared between the two outputs, you will also use a ResNet style skip connection in the model. If you are familiar with Keras, you have probably come across examples of models that are trained to perform multiple tasks. For example, an object detection model where a CNN is trained to find all class instances in the input images as well as give a regression output to localize the detected class instances in the input. Being able to use Keras' functional API is a first step towards building complex, multi-output models like object detection models. We will be using TensorFlow as our machine learning framework. The project uses the Google Colab environment. You will need prior programming experience in Python. You will also need prior experience with Keras. Consider this to be an intermediate level Keras project. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like gradient descent but want to understand how to use use Keras to write custom, more complex models than just plain sequential neural networks. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Requirements

Prior programming experience in Python. Conceptual understanding of Neural Networks. Prior experience with TensorFlow and Keras is recommended.

Skills you will develop

  • Deep Learning

  • Machine Learning

  • Tensorflow

  • Computer Vision

  • keras

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. Introduction

  2. Create Dataset

  3. Dataset Generator

  4. Create Model

  5. Train the Model

  6. Final Predictions

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

Reviews

TOP REVIEWS FROM CREATING MULTI TASK MODELS WITH KERAS

View all reviews

Frequently Asked Questions

Because your workspace contains a cloud desktop that is sized for a laptop or desktop computer, Guided Projects are not available on your mobile device.

Guided Project instructors are subject matter experts who have experience in the skill, tool or domain of their project and are passionate about sharing their knowledge to impact millions of learners around the world.

You can download and keep any of your created files from the Guided Project. To do so, you can use the “File Browser” feature while you are accessing your cloud desktop.

At the top of the page, you can press on the experience level for this Guided Project to view any knowledge prerequisites. For every level of Guided Project, your instructor will walk you through step-by-step.

Yes, everything you need to complete your Guided Project will be available in a cloud desktop that is available in your browser.

You'll learn by doing through completing tasks in a split-screen environment directly in your browser. On the left side of the screen, you'll complete the task in your workspace. On the right side of the screen, you'll watch an instructor walk you through the project, step-by-step.