All the steps we performed till now remains same for the cloud as well. But there are few additional modules required to configure the cloud virtual machines to make your DL applications servable and scalable. So before setting up your server follow the instructions from the preceding section.
To deploy your Deep Learning applications in the cloud you will need a server which is good enough to train your models and serve at the same time, so with the huge development in Deep Learning space, the need for cloud servers to practice and deploy the projects has increased drastically and so the options in the market. Here is the list of best options which one can opt for:
- PaperSpace (https://www.paperspace.com/)
- FloydHub (https://www.floydhub.com)
- Amazon Web Services (https://aws.amazon.com/)
- Google Cloud Platform (https://cloud.google.com/)
- Digital Ocean (https://cloud.digitalocean.com/)
All the previously-mentioned options have some pro and cons and it totally depends on your use-case and preferences. So feel free to explore more. In this book, we will build and deploy our models mostly on Google Compute Engine (GCE) which is a part of Google Cloud Platform (GCP), you follow these steps to spin up a VM server and get started: