9️⃣ Make predictions

Now that our deployment is fully set up, we can perform inference on the model to get predictions.

This part can only be done using the python SDK, so we strongly recommend you rely on the associated documentation available here.

Once the prediction is done, the monitoring dashboard of the deployment should be updated. The metrics are updated in real-time according to the predictions made by the model.

The “Predictions” view allows you to review the predictions done by the model and particularly to review them in order to submit them in the feedback loop as defined in the settings.

As soon as the number of images submitted to the feedback loop reaches the threshold defined the in the continuous training part of the settings, a new experiment is automatically launched on the related project with the predefined parameters. Once the experiment is over, it will be exported as a new version of the currently deployed model.