Deployments

Important

The expected color code is RGB for Intel® Geti™ exportable code and deployment.

The Deployments screen allows users to export deployment code for the trained models.

Once you have tested and optimized the model, you are ready to download and deploy your solution. To download the code, click on Select model for deployment. In the dialog box, choose the model architecture and its version as well as the model optimization if available. In the case of a task chain project, you will need to select two models through a wizard. Upon your selection, click Download. Additionally, you can choose between Code Deployment and OpenVINO™ Model Server Deployment.

Code Deployment

Code Deployment works with the Intel® Geti™ SDK and allows to interact with an Intel® Geti™ server via the REST API which provides functionality for:

• Project creation from datasets on disk

• Project download (images, videos, configuration, annotations, predictions and models)

• Project creation and upload from a previous download

• Deploying a project for local inference with OpenVINO

• Getting and setting project and model configuration

• Launching and monitoring training jobs

• Media upload and prediction

Go to the GitHub repository to download the SDK. The repository also contains a set of (tutorial style) Jupyter notebooks that demonstrate how to use the SDK. We highly recommend checking them out to get a feeling for use cases for the package.

OpenVINO™ Model Server Deployment

OpenVINO™ Model Server Deployment allows to deploy Intel® Geti™ models on OpenVINO™ Model Server Docker container and access it using easy to use HTTP interface.

This approach makes serving your models outside of Intel® Geti™ platform easier, e.g. on an Edge node device, or on your laptop.

Additionally, straightforward HTTP interface allows you to integrate results of model predictions with other applications.

For a more technical description, please refer to README.md file included in OpenVINO™ Model Server Deployment package.