Deploying a Pytorch Computer Vision Model API to Heroku

Offered By
In this Guided Project, you will:

Build a PyTorch computer vision model REST API with Flask.

Deploy PyTorch computer vision model REST API to Heroku.

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

Welcome to the “Deploying a Pytorch Computer Vision Model API to Heroku” guided project. Computer vision is one of the prominent fields of AI with numerous applications in the real world including self-driving cars, image recognition, and object tracking, among others. The ability to make models available for real-world use is an essential skill anyone interested in AI engineering should have especially for computer vision and this is why this project exists. In this project, we will deploy a Flask REST API using one of Pytorch's pre-trained computer vision image classification models. This API will be able to receive an image, inference the pre-trained model, and return its predicted classification. This project is an intermediate python project for anyone interested in learning about how to productionize Pytorch computer vision models in the real world via a REST API on Heroku. It requires preliminary knowledge on how to build and train PyTorch models (as we will not be building or training models), how to utilize Git and a fundamental understanding of REST APIs. Learners would also need a Heroku account and some familiarity with the Python Flask module and the Postman API Platform. At the end of this project, learners will have a publicly available API they can use to demonstrate their knowledge in deploying computer vision models.

Skills you will develop

  • Machine Learning

  • Python Programming

  • pytorch

  • Machine Learning Deployment

  • Computer Vision

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. Import all the necessary libraries.

  2. Build a PyTorch computer vision model REST API with Flask.

  3. Build a simple flask web server.

  4. Test out PyTorch computer vision model REST API localhost end point.

  5. Deploy PyTorch computer vision model REST API to Heroku

  6. Test out PyTorch computer vision model REST API Heroku end point.

  7. Capstone Practice

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

By purchasing a Guided Project, you'll get everything you need to complete the Guided Project including access to a cloud desktop workspace through your web browser that contains the files and software you need to get started, plus step-by-step video instruction from a subject matter expert.

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.

Guided Projects are not eligible for refunds. See our full refund policy.

Financial aid is not available for Guided Projects.

Auditing is not available for Guided Projects.

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.