Deploying a Pytorch Computer Vision Model API to Heroku
Offered By: Coursera Project Network via Coursera
Course Description
Overview
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.
Syllabus
- Project Overview
- 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.
Taught by
Emmanuel Acheampong
Related Courses
2D image processingHigher School of Economics via Coursera 3D Reconstruction - Multiple Viewpoints
Columbia University via Coursera 3D Reconstruction - Single Viewpoint
Columbia University via Coursera Post Graduate Certificate in Advanced Machine Learning & AI
Indian Institute of Technology Roorkee via Coursera Advanced Computer Vision with TensorFlow
DeepLearning.AI via Coursera