Activity Recognition using Python, Tensorflow and Keras

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

Learn about data augmentation.

Learn about transfer learning using training the pre-trained model InceptionNet V3 on the data.

Clock1.5 hours
BeginnerBeginner
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

Note: The rhyme platform currently does not support webcams, so this is not a live project. This guided project is about human activity recognition using Python,TensorFlow2 and Keras. Human activity recognition comes under the computer vision domain. In this project you will learn how to customize the InceptionNet model 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.Manually label images. 2. Learn how to use data augmentation normalization. 3. Learn about transfer learning using training the pre-trained model InceptionNet V3 on the data. 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 LearningPython ProgrammingTensorflowcognitive data sciencekeras

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. Learn how to normalize data to improve accuracy of the final results.

  2. Learn how to fine tune the model to improve it's accuracy.

  3. Learn how to apply transfer learning using InceptionNet V3.

  4. Learn how to augment data to prevent overfitting of the model.

  5. Learn how to label data manually as 0 or 1.

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.