Creating Multi Task Models With Keras
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.
Buy Now Free
- Level Intermediate
- Duration 3 hours
- Course by Coursera Project Network
-
Offered by
About
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.Modules
Creating Multi Task Models with Keras
-
1
Readings
-
1
Plugin
-
1
Lab
-
1
Assignment
1
Assignment
- Graded Quiz: Test your Project Understanding
1
Labs
- Creating Multi Task Models with Keras
1
Readings
- Project-based Course Overview
Auto Summary
"Creating Multi Task Models With Keras" is a 1-hour guided project designed for IT & Computer Science professionals. Led by Coursera, this intermediate-level course focuses on using Keras' functional API to build multi-task, multi-output models. Learners will gain hands-on experience with TensorFlow and Google Colab, enhancing their skills to create complex models like object detection. Prior knowledge of Python, Keras, and neural networks is required. Available through a Starter subscription, this course is especially suited for North American learners.
Amit Yadav