创建批量预测作业

使用 create_batch_prediction_job 方法创建批量预测作业。

深入探索

如需查看包含此代码示例的详细文档,请参阅以下内容:

代码示例

Java

在尝试此示例之前,请按照《Vertex AI 快速入门:使用客户端库》中的 Java 设置说明执行操作。 如需了解详情,请参阅 Vertex AI Java API 参考文档

如需向 Vertex AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

import com.google.cloud.aiplatform.util.ValueConverter;
import com.google.cloud.aiplatform.v1.AcceleratorType;
import com.google.cloud.aiplatform.v1.BatchDedicatedResources;
import com.google.cloud.aiplatform.v1.BatchPredictionJob;
import com.google.cloud.aiplatform.v1.GcsDestination;
import com.google.cloud.aiplatform.v1.GcsSource;
import com.google.cloud.aiplatform.v1.JobServiceClient;
import com.google.cloud.aiplatform.v1.JobServiceSettings;
import com.google.cloud.aiplatform.v1.LocationName;
import com.google.cloud.aiplatform.v1.MachineSpec;
import com.google.cloud.aiplatform.v1.ModelName;
import com.google.protobuf.Value;
import java.io.IOException;

public class CreateBatchPredictionJobSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String project = "PROJECT";
    String displayName = "DISPLAY_NAME";
    String modelName = "MODEL_NAME";
    String instancesFormat = "INSTANCES_FORMAT";
    String gcsSourceUri = "GCS_SOURCE_URI";
    String predictionsFormat = "PREDICTIONS_FORMAT";
    String gcsDestinationOutputUriPrefix = "GCS_DESTINATION_OUTPUT_URI_PREFIX";
    createBatchPredictionJobSample(
        project,
        displayName,
        modelName,
        instancesFormat,
        gcsSourceUri,
        predictionsFormat,
        gcsDestinationOutputUriPrefix);
  }

  static void createBatchPredictionJobSample(
      String project,
      String displayName,
      String model,
      String instancesFormat,
      String gcsSourceUri,
      String predictionsFormat,
      String gcsDestinationOutputUriPrefix)
      throws IOException {
    JobServiceSettings settings =
        JobServiceSettings.newBuilder()
            .setEndpoint("us-central1-aiplatform.googleapis.com:443")
            .build();
    String location = "us-central1";

    // 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 (JobServiceClient client = JobServiceClient.create(settings)) {

      // Passing in an empty Value object for model parameters
      Value modelParameters = ValueConverter.EMPTY_VALUE;

      GcsSource gcsSource = GcsSource.newBuilder().addUris(gcsSourceUri).build();
      BatchPredictionJob.InputConfig inputConfig =
          BatchPredictionJob.InputConfig.newBuilder()
              .setInstancesFormat(instancesFormat)
              .setGcsSource(gcsSource)
              .build();
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(gcsDestinationOutputUriPrefix).build();
      BatchPredictionJob.OutputConfig outputConfig =
          BatchPredictionJob.OutputConfig.newBuilder()
              .setPredictionsFormat(predictionsFormat)
              .setGcsDestination(gcsDestination)
              .build();
      MachineSpec machineSpec =
          MachineSpec.newBuilder()
              .setMachineType("n1-standard-2")
              .setAcceleratorType(AcceleratorType.NVIDIA_TESLA_T4)
              .setAcceleratorCount(1)
              .build();
      BatchDedicatedResources dedicatedResources =
          BatchDedicatedResources.newBuilder()
              .setMachineSpec(machineSpec)
              .setStartingReplicaCount(1)
              .setMaxReplicaCount(1)
              .build();
      String modelName = ModelName.of(project, location, model).toString();
      BatchPredictionJob batchPredictionJob =
          BatchPredictionJob.newBuilder()
              .setDisplayName(displayName)
              .setModel(modelName)
              .setModelParameters(modelParameters)
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .setDedicatedResources(dedicatedResources)
              .build();
      LocationName parent = LocationName.of(project, location);
      BatchPredictionJob response = client.createBatchPredictionJob(parent, batchPredictionJob);
      System.out.format("response: %s\n", response);
      System.out.format("\tName: %s\n", response.getName());
    }
  }
}

Python

在尝试此示例之前,请按照《Vertex AI 快速入门:使用客户端库》中的 Python 设置说明执行操作。 如需了解详情,请参阅 Vertex AI Python API 参考文档

如需向 Vertex AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

from google.cloud import aiplatform
from google.protobuf import json_format
from google.protobuf.struct_pb2 import Value


def create_batch_prediction_job_sample(
    project: str,
    display_name: str,
    model_name: str,
    instances_format: str,
    gcs_source_uri: str,
    predictions_format: str,
    gcs_destination_output_uri_prefix: str,
    location: str = "us-central1",
    api_endpoint: str = "us-central1-aiplatform.googleapis.com",
):
    # The AI Platform services require regional API endpoints.
    client_options = {"api_endpoint": api_endpoint}
    # Initialize client that will be used to create and send requests.
    # This client only needs to be created once, and can be reused for multiple requests.
    client = aiplatform.gapic.JobServiceClient(client_options=client_options)
    model_parameters_dict = {}
    model_parameters = json_format.ParseDict(model_parameters_dict, Value())

    batch_prediction_job = {
        "display_name": display_name,
        # Format: 'projects/{project}/locations/{location}/models/{model_id}'
        "model": model_name,
        "model_parameters": model_parameters,
        "input_config": {
            "instances_format": instances_format,
            "gcs_source": {"uris": [gcs_source_uri]},
        },
        "output_config": {
            "predictions_format": predictions_format,
            "gcs_destination": {"output_uri_prefix": gcs_destination_output_uri_prefix},
        },
        "dedicated_resources": {
            "machine_spec": {
                "machine_type": "n1-standard-2",
                "accelerator_type": aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,
                "accelerator_count": 1,
            },
            "starting_replica_count": 1,
            "max_replica_count": 1,
        },
    }
    parent = f"projects/{project}/locations/{location}"
    response = client.create_batch_prediction_job(
        parent=parent, batch_prediction_job=batch_prediction_job
    )
    print("response:", response)

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例,请参阅 Google Cloud 示例浏览器