In this project, you'll learn how to launch an object detection web app capable of object detection in a serverless environment. This interactive web app has already been created using Flask, a popular micro-framework for Python. The object detection web app we are building runs on a Faster R-CNN (Region based Convolutional Neural Network) algorithm that takes in an image, and outputs the same image but with boxes around the detected objects along with a confidence percentage. The focus of this lab is to learn how Docker can help us containerize our application and deploying it as a serverless app on IBM Code Engine to share with all your friends!

Serverless has quickly become one of the hottest topics among developers, but what is it exactly? Serverless is a cloud-native deployment model that allows developers to build and run applications without having to manage servers and other infrastructure. Once deployed, serverless apps respond to demand and automatically scale up and down as needed. Serverless offerings from public cloud providers are usually metered based on demand. As a result, when a serverless function is sitting idle, it doesn’t cost anything.

After completing this project, you will be able to
-  Describe how you can build a python appplication in a Docker image
-  Understand basic Docker commands to run Docker containers
-  Deploy your object detection web app to IBM Code Engine

Firstly, you just need a web browser!  Regarding prior skills,  you will also need basic Python knowledge if you wish to dive into the web app and understand how it works.

Everything else is provided to you via the IBM Skills Network Labs environment, where you will have access to the Cloud IDE and a Docker installation that we offer as part of the IBM Skills Network Labs environment. 

This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari.

Richard Ye, IBM