Deployment

Publish the trained model so your Pops can run it

As you enter the deployment step, you will see information about your model including its name, version, the number of images it was trained on, and the date it was trained.

To combine this model with others — text detection inside the detected object, person key points, tracking across video frames, segmentation masks — chain them as components in a Pop. See Components and Examples.

Deployment location

Choose where to deploy your model.

Deploy to Cloud - EyePop.ai Pop — click Create a Pop to create a Pop that you can then re-use for your dashboard as an API endpoint for your code. An AI worker server in EyePop.ai does the analysis and the model is tested in the cloud.

Deploy to the Edge (powered by Qualcomm AI Hub) allows you to run the model on Snapdragon devices and provides code examples to walk you through that process.

For Example Architectures, please see deployments in the left hand menu.