271 - How to deploy your trained machine learning model as a web app on Heroku (with docker)

Code generated in the video can be downloaded from here: This video demonstrates the process of deploying your trained deep learning model as a browser-based app on Heroku by deploying a Docker container. It uses HAM10000 trained model to predict skin cancer type for the image supplied by the user. This application is exactly the same as the one from video 270 except here we use Docker. Some useful commands: Please install Heroku CLI on your system. To log in to your Heroku account from CLI: heroku login -i​ To scale dynos for your app: heroku ps:scale web=1 --app app_name Docker: Please install Docker on your system (e.g. Docker for Windows) Our app name from this video is used as an example for the following commands. To build an image using the Docker file: docker image build -t skincancer-app . List Docker images: docker image ls To run Docker on a specific port: docker run -p 5000:5000 -d skincancer-app Open the URL to check your app. http