Creating Multi Task Models With Keras
67 ratings

3,602 already enrolled
Creating multi-task models with Keras
Training multi-task models with Keras
Showcase this hands-on experience in an interview
67 ratings
3,602 already enrolled
Creating multi-task models with Keras
Training multi-task models with Keras
Showcase this hands-on experience in an interview
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.
Prior programming experience in Python. Conceptual understanding of Neural Networks. Prior experience with TensorFlow and Keras is recommended.
Deep Learning
Machine Learning
Tensorflow
Computer Vision
keras
In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:
Introduction
Create Dataset
Dataset Generator
Create Model
Train the Model
Final Predictions
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
by SK
Feb 22, 2021The project was simple yet provided the core idea of going for multitask model with an interesting use-case.
by MS
May 14, 2021Amit is awesome. You are one the best instructors/teachers , I have ever seen in my life.
by CM
Feb 5, 2022An useful practice and review of keras functional api.
by KK
Feb 24, 2023Fantastic course and very easy to follow on implementing multi-task learning on the MNIST dataset. Thank you very much!
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.
More questions? Visit the Learner Help Center.