FastAI Deployment

Deploy your own Model

Deploying your on model is a easy as replacing the model (server/export.pkl) with your own model. Of course, it makes sense to also modify the HTML/CSS a bit to your liking.

Command to launch the container:

docker build -t churros_samosa_classifier . && docker run --rm -it -p 5000:5000 churros_samosa_classifier

Then you can deploy the Container to any Cloud Provider of your choosing.

I recommend Render, which is what I used for my deployment but everything else should work fine, too.

Steps for deploying on Render

• Fork this repository

• Replace the model (export.pkl)

• Change the HTML and CSS to your liking

• In the Render Dashboard create a new Web Service

• Link your repository

• Make sure Docker is selected

• Done!