Chevron Left
Back to Creating Multi Task Models With Keras

Learner Reviews & Feedback for Creating Multi Task Models With Keras by Coursera Project Network

4.7
stars
78 ratings

About the Course

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....

Top reviews

MS

May 15, 2021

Amit is awesome. You are one the best instructors/teachers , I have ever seen in my life.

CM

Feb 6, 2022

A​n useful practice and review of keras functional api.

Filter by:

1 - 13 of 13 Reviews for Creating Multi Task Models With Keras

By GOSU P

•

Jul 2, 2021

This course is pretty good, that I learned many concepts in one hour. The instructor too very good that his way of explanation made me to understand it quickly.

By Kamalpreet K

•

Feb 25, 2023

Fantastic course and very easy to follow on implementing multi-task learning on the MNIST dataset. Thank you very much!

By Mohd. F I S

•

May 16, 2021

Amit is awesome. You are one the best instructors/teachers , I have ever seen in my life.

By Chow K M

•

Feb 7, 2022

An useful practice and review of keras functional api.

By Kenneth N

•

Jun 30, 2022

exceptional and very clear. great project

By Shadi Q

•

Jan 20, 2023

Small project, great content!

By Shahid N K

•

Apr 22, 2022

Excellent guided project

By Oshan J

•

Jan 6, 2022

extremely valueble

By Libero P

•

Sep 8, 2025

Πολύ καλό μάθημα.

By Tưởng N H

•

Jun 28, 2021

great course

By Sanjay K

•

Feb 23, 2021

The project was simple yet provided the core idea of going for multitask model with an interesting use-case.

By Jing Z

•

Feb 19, 2021

Great lesson!

By MBT18CS085 N S

•

Jun 10, 2022

keras