After your AutoML image classification model is done training, use theGoogle Cloud console to create an endpoint and deploy your model tothe endpoint. After your model is deployed to this new endpoint, send an imageto the model for label prediction.

This tutorial has several pages:

1. Set up your project and environment.

2. Create an image classification dataset, and import images.

3. Train an AutoML image classification model.

4. Evaluate and analyze model performance.

5. Deploy a model to an endpoint, and send a prediction.

6. Clean up your project.

Each page assumes that you have already performed the instructions from theprevious pages of the tutorial.

Deploy your model to an endpoint

Access your trained model to deploy it to a new or existing endpoint fromthe Models page:

1. In the Google Cloud console, in the Vertex AI section, go totheTraining page.

   Go to the Training page

2. Select your trained AutoML model. This takes you to theEvaluate tab where you can view model performance metrics.

3. Choose thetabDeploy & test tab.

4. ClickDeploy to endpoint.

5. Chooseradio_button_checkedCreate newendpoint, set the endpoint name tohello_automl_image, then clickContinue.

6. InModel settings, accept theTraffic split of100%, enter1 inNumber of compute nodes, then clickDone.

7. ClickDeploy to deploy your model to your new endpoint.

It takes several minutes to create the endpoint and deploy the AutoML modelto the new endpoint.

Send a prediction to your model

After the endpoint creation process finishes you can send a single imageannotation (prediction) request in the Google Cloud console.

1. Navigate to the "Test your model" section of the sameDeploy & test tabyou used to create an endpoint in the previous step(Models >your_model >tab Deploy & test).

2. ClickUpload image and choose a locally saved image for prediction, andview its predicted label.

   

What's next

Follow thelast page of the tutorial to clean upresources that you have created.