This documentation is for AutoML Vision, which is different from Vertex AI. If you are using Vertex AI, see the Vertex AI documentation.

Update a model's node number

Deploys a model with an updated node count.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

Code sample

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// visionClassificationDeployModelWithNodeCount deploys a model with node count.
func visionClassificationDeployModelWithNodeCount(w io.Writer, projectID string, location string, modelID string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "ICN123456789..."

	ctx := context.Background()
	client, err := automl.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.DeployModelRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		ModelDeploymentMetadata: &automlpb.DeployModelRequest_ImageClassificationModelDeploymentMetadata{
			ImageClassificationModelDeploymentMetadata: &automlpb.ImageClassificationModelDeploymentMetadata{
				NodeCount: 2,
			},
		},
	}

	op, err := client.DeployModel(ctx, req)
	if err != nil {
		return fmt.Errorf("DeployModel: %v", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

	if err := op.Wait(ctx); err != nil {
		return fmt.Errorf("Wait: %v", err)
	}

	fmt.Fprintf(w, "Model deployed.\n")

	return nil
}

Java

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.automl.v1beta1.AutoMlClient;
import com.google.cloud.automl.v1beta1.DeployModelRequest;
import com.google.cloud.automl.v1beta1.ImageClassificationModelDeploymentMetadata;
import com.google.cloud.automl.v1beta1.ModelName;
import com.google.cloud.automl.v1beta1.OperationMetadata;
import com.google.protobuf.Empty;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class ClassificationDeployModelNodeCount {

  // Deploy a model with a specified node count
  static void classificationDeployModelNodeCount(String projectId, String modelId)
      throws IOException, ExecutionException, InterruptedException {
    // String projectId = "YOUR_PROJECT_ID";
    // String modelId = "YOUR_MODEL_ID";

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (AutoMlClient client = AutoMlClient.create()) {
      // Get the full path of the model.
      ModelName modelFullId = ModelName.of(projectId, "us-central1", modelId);

      // Set how many nodes the model is deployed on
      ImageClassificationModelDeploymentMetadata deploymentMetadata =
          ImageClassificationModelDeploymentMetadata.newBuilder().setNodeCount(2).build();

      DeployModelRequest request =
          DeployModelRequest.newBuilder()
              .setName(modelFullId.toString())
              .setImageClassificationModelDeploymentMetadata(deploymentMetadata)
              .build();
      // Deploy the model
      OperationFuture<Empty, OperationMetadata> future = client.deployModelAsync(request);
      future.get();
      System.out.println("Model deployment on 2 nodes finished");
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';

// Imports the Google Cloud AutoML library
const {AutoMlClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new AutoMlClient();

async function deployModelWithNodeCount() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    imageClassificationModelDeploymentMetadata: {
      nodeCount: 2,
    },
  };

  const [operation] = await client.deployModel(request);

  // Wait for operation to complete.
  const [response] = await operation.promise();
  console.log(`Model deployment finished. ${response}`);
}

deployModelWithNodeCount();

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"

client = automl.AutoMlClient()
# Get the full path of the model.
model_full_id = client.model_path(project_id, "us-central1", model_id)

# node count determines the number of nodes to deploy the model on.
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#imageclassificationmodeldeploymentmetadata
metadata = automl.ImageClassificationModelDeploymentMetadata(node_count=2)

request = automl.DeployModelRequest(
    name=model_full_id, image_classification_model_deployment_metadata=metadata
)
response = client.deploy_model(request=request)

print("Model deployment finished. {}".format(response.result()))

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.