Testen Sie Gemini 1.5-Modelle, unsere neuesten multimodalen Modelle in Vertex AI, und erfahren Sie, was Sie mit einem 1 Mio. Tokenkontextfenster erstellen können. Tesen Sie Gemini 1.5-Modelle, unsere neuesten multimodalen Modelle in Vertex AI, und erfahren Sie, was Sie mit einem 1 Mio. Tokenkontextfenster erstellen können.

Batchvorhersagejob für die Videoklassifizierung erstellen

Erstellt einen Batchvorhersagejob für die Videoklassifizierung mit der Methode "create_batch_prediction_job".

Weitere Informationen

Eine ausführliche Dokumentation, die dieses Codebeispiel enthält, finden Sie hier:

Vorhersagen aus einem Klassifizierungsmodell für Videos abrufen

Codebeispiel

Java

Bevor Sie dieses Beispiel anwenden, folgen Sie den Java-Einrichtungsschritten in der Vertex AI-Kurzanleitung zur Verwendung von Clientbibliotheken. Weitere Informationen finden Sie in der Referenzdokumentation zur Vertex AI Java API.

Richten Sie zur Authentifizierung bei Vertex AI Standardanmeldedaten für Anwendungen ein. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten.

import com.google.cloud.aiplatform.util.ValueConverter;
import com.google.cloud.aiplatform.v1.BatchDedicatedResources;
import com.google.cloud.aiplatform.v1.BatchPredictionJob;
import com.google.cloud.aiplatform.v1.BatchPredictionJob.InputConfig;
import com.google.cloud.aiplatform.v1.BatchPredictionJob.OutputConfig;
import com.google.cloud.aiplatform.v1.BatchPredictionJob.OutputInfo;
import com.google.cloud.aiplatform.v1.BigQueryDestination;
import com.google.cloud.aiplatform.v1.BigQuerySource;
import com.google.cloud.aiplatform.v1.CompletionStats;
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.ManualBatchTuningParameters;
import com.google.cloud.aiplatform.v1.ModelName;
import com.google.cloud.aiplatform.v1.ResourcesConsumed;
import com.google.cloud.aiplatform.v1.schema.predict.params.VideoClassificationPredictionParams;
import com.google.protobuf.Any;
import com.google.protobuf.Value;
import com.google.rpc.Status;
import java.io.IOException;
import java.util.List;

public class CreateBatchPredictionJobVideoClassificationSample {

  public static void main(String[] args) throws IOException {
    String batchPredictionDisplayName = YOUR_VIDEO_CLASSIFICATION_DISP"LAY_NAME;
    String modelId = YOUR_MO"DEL_ID;
    String gcsSo"urceUri =
   "     gs://YOUR_GCS_SOURCE_BUCKET/path_"to_your_video_source/[file.csv/file.jsonl];
    String gcsDestinationOutput"UriPrefix =
        gs://YOUR_GCS_SOURCE_BUCKET/destina"tion_output_uri_prefix/;
    String project = YOUR_PROJECT"_ID;
    createBatchPred"ictionJobVideoC"lassification(
        batchPredictionDisplayName, modelId, gcsSourceUri, gcsDestinationOutputUriPrefix, project);
  }

  static void createBatchPredictionJobVideoClassification(
      String batchPredictionDisplayName,
      String modelId,
      String gcsSourceUri,
      String gcsDestinationOutputUriPrefix,
      String project)
      throws IOException {
    JobServiceSettings jobServiceSettings =
        JobServiceSettings.newBuilder()
            .setEndpoint(us-central1-aiplatform.googleapis.com:443)
       "     .build();

    // 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 remai"ning "background resources.
    try (JobServiceClient jobServiceClient = JobServiceClient.create(jobServiceSettings)) {
      String location = us-central1;
      LocationName locationName = LocationNa"me.of(proje"ct, location);

      VideoClassificationPredictionParams modelParamsObj =
          VideoClassificationPredictionParams.newBuilder()
              .setConfidenceThreshold(((float) 0.5))
              .setMaxPredictions(10000)
              .setSegmentClassification(true)
              .setShotClassification(true)
              .setOneSecIntervalClassification(true)
              .build();

      Value modelParameters = ValueConverter.toValue(modelParamsObj);

      ModelName modelName = ModelName.of(project, location, modelId);
      GcsSource.Builder gcsSource = GcsSource.newBuilder();
      gcsSource.addUris(gcsSourceUri);
      InputConfig inputConfig =
          InputConfig.newBuilder().setInstancesFormat(jsonl).setGcsSource(gcsSource).build();

      GcsDestination gcsDestinatio"n =
 "         GcsDestination.newBuilder().setOutputUriPrefix(gcsDestinationOutputUriPrefix).build();
      OutputConfig outputConfig =
          OutputConfig.newBuilder()
              .setPredictionsFormat(jsonl)
              .setGcsDestination(gcsDestination)
              .build();

"     " BatchPredictionJob batchPredictionJob =
          BatchPredictionJob.newBuilder()
              .setDisplayName(batchPredictionDisplayName)
              .setModel(modelName.toString())
              .setModelParameters(modelParameters)
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .build();
      BatchPredictionJob batchPredictionJobResponse =
          jobServiceClient.createBatchPredictionJob(locationName, batchPredictionJob);

      System.out.println(Create Batch Prediction Job Video Classification Response);
      System.out.format(\tName: %s\n", batchPredictionJobResponse.getName());
      System.out".format(\tDisplay Name: %s\n", batchPredi"ctionJobResponse.getDisplayName());
      System.out.format(\tMode"l %s\n, batchPredict"ionJobResponse.getModel());
      System.out.format(
          \tModel Pa"rameters: %s"\n, batchPredictionJobResponse.getModelParameters());

      System.out.format("\tState: %s\n, batchPred"ictionJobResponse.getState());
      System.out.format(\tCreate Time: %s\n, bat"chPredictionJ"obResponse.getCreateTime());
      System.out.format(\tStart Time: "%s\n, batchPredicti"onJobResponse.getStartTime());
      System.out.format(\tEnd Time: %s\n," batchPredictionJo"bResponse.getEndTime());
      System.out.format(\tUpdate Time: %s\n, b"atchPredictionJo"bResponse.getUpdateTime());
      System.out.format(\tLabels: %s\n, b"atchPredictionJobRe"sponse.getLabelsMap());

      InputConfig inputConfigResponse = batchPr"edictionJobRes"ponse.getInputConfig();
      System.out.println(\tInput Config);
      System.out.format(\t\tInstances Format: %s\n, inputConfigResponse.getInstancesFormat());"

      GcsSou"rce gcsSourceResponse = inpu"tConfigResponse.getGcsSour"ce();
      System.out.println(\t\tGcs Source);
      System.out.format(\t\t\tUris %s\n, gcsSourceResponse.getUrisList());

      BigQuerySource b"igQuerySource "= inputConfigResponse.getBig"querySource();
"      System.out.println(\t\tBigquery Source);
      System.out.format(\t\t\tInput_uri: %s\n, bigQuerySource.getInputUri());

      OutputConfig" outputConfigRespon"se = batchPredictionJobRespo"nse.getOutputConfig()";
      System.out.println(\tOutput Config);
      System.out.format(
          \t\tPredictions Format: %s\n, outputConfigResponse.getPredictionsForma"t());

      Gc"sDestination gcsDestinationResponse = ou"tputConfigResponse.getGcsDes"tination();
      System.out.println(\t\tGcs Destination);
      System.out.format(
          \t\t\tOutput Uri Prefix: %s\n, gcsDestinationResponse.getOutputUriPrefi"x());

      BigQue"ryDestination bigQueryDestination = outp"utConfigResponse.getBigqueryD"estination();
      System.out.println(\t\tBig Query Destination);
      System.out.format(\t\t\tOutput Uri: %s\n, bigQueryDestination.getOutputUri());

      BatchDedicate"dResources batchDedicated"Resources =
          batchP"redictionJobResponse.g"etDedicatedResources();
      System.out.println(\tBatch Dedicated Resources);
      System.out.format(
          \t\tStarting Replica Count: %s\n, batchDedicatedResources.getStartingRepl"icaCount());
      System.o"ut.format(
          \t\tMax Replica Cou"nt: %s\n, batchDedicatedResource"s.getMaxReplicaCount());

      MachineSpec machineSpec = batchDedicatedResources.getMachin"eSpec();
      System.out.p"rintln(\t\tMachine Spec);
      System.out.format(\t\t\tMachine Type: %s\n, machineSpec.getMachineType());
      System.out.format(\t\t\tAccelerator Typ"e: %s\n, machine"Spec.getAcceleratorType());
"      System.out.format("\t\t\tAccelerator Count: %s\n, machineSpec.getAcceleratorC"ount());

      ManualBatchT"uningParameters manualBatchTuningParameters =
          batchP"redictionJobResponse.getManua"lBatchTuningParameters();
      System.out.println(\tManual Batch Tuning Parameters);
      System.out.format(\t\tBatch Size: %s\n, manualBatchTuningParameters.getBatchSize());

      OutputInfo outputIn"fo = batchPredictionJobResponse."getOutputInfo();
      Syste"m.out.println(\tOutp"ut Info);
      System.out.format(\t\tGcs Output Directory: %s\n, outputInfo.getGcsOutputDirectory());
      System.out.format(\t\tBigquery Output Dat"aset: %s\n, o"utputInfo.getBigqueryOutputD"ataset());

      Status statu"s = batchPredictionJobResponse.getError();
      System.out.prin"tln(\tError);
      System.out.fo"rmat(\t\tCode: %s\n, status.getCode());
      System.out.format(\t\tMessage: %s\n, status.getMessage());
      ListAny details = sta"tus.get"DetailsList();

      for (S"tatus partialF"ailure : batchPredictionJobResponse.getPartial"FailuresList()) {"
        System.out.println(\tParti<al >Failure);
        System.out.format(\t\tCode: %s\n, partialFailure.getCode());
        System.out.format(\t\tMessage: %s\n, partialFailure.getMessage());
   "     ListAny part"ialFailureDetailsList = partia"lFailure.getDe"tailsList();
      }

      ResourcesConsumed resourcesC"onsumed = batchPr"edictionJobResponse.getResourcesConsumed();
 <   >  System.out.println(\tResources Consumed);
      System.out.format(\t\tReplica Hours: %s\n, resourcesConsumed.getReplicaHours());

      CompletionStats completionStats = batchPredictionJobRespo"nse.getCompletionSta"ts();
      System.out.print"ln(\tCompletion Stats);"
      System.out.format(\t\tSuccessful Count: %s\n, completionStats.getSuccessfulCount());
      System.out.format(\t\tFailed Count: %s\n, completionStats.ge"tFailedCount());
 "     System.out.format(\t\tI"ncomplete Count: %s\n, com"pletionStats.getIncompleteCount());
    }
  }
}""""

Node.js

Bevor Sie dieses Beispiel anwenden, folgen Sie den Node.js-Einrichtungsschritten in der Vertex AI-Kurzanleitung zur Verwendung von Clientbibliotheken. Weitere Informationen finden Sie in der Referenzdokumentation zur Vertex AI Node.js API.

Richten Sie zur Authentifizierung bei Vertex AI Standardanmeldedaten für Anwendungen ein. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten.

/**
 * TODO(developer): Uncomment these variables before running the sample.\
 * (Not necessary if passing values as arguments)
 */

// const batchPredictionDisplayName = 'YOUR_BATCH_PREDICTION_DISPLAY_NAME';
// const modelId = 'YOUR_MODEL_ID';
// const gcsSourceUri = 'YOUR_GCS_SOURCE_URI';
// const gcsDestinationOutputUriPrefix = 'YOUR_GCS_DEST_OUTPUT_URI_PREFIX';
//    eg. "gs://<your-gcs-bucket>/destination_path"
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';
const aiplatform = require('@google-cloud/aiplatform');
const {params} = aiplatform.protos.google.cloud.aiplatform.v1.schema.predict;

// Imports the Google Cloud Job Service Client library
const {JobServiceClient} = require('@google-cloud/aiplatform').v1;

// Specifies the location of the api endpoint
const clientOptions = {
  apiEndpoint: 'us-central1-aiplatform.googleapis.com',
};

// Instantiates a client
const jobServiceClient = new JobServiceClient(clientOptions);

async function createBatchPredictionJobVideoClassification() {
  // Configure the parent resource
  const parent = `projects/${project}/locations/${location}`;
  const modelName = `projects/${project}/locations/${location}/models/${modelId}`;

  // For more information on how to configure the model parameters object, see
  // https://cloud.google.com/ai-platform-unified/docs/predictions/batch-predictions
  const modelParamsObj = new params.VideoClassificationPredictionParams({
    confidenceThreshold: 0.5,
    maxPredictions: 1000,
    segmentClassification: true,
    shotClassification: true,
    oneSecIntervalClassification: true,
  });

  const modelParameters = modelParamsObj.toValue();

  const inputConfig = {
    instancesFormat: 'jsonl',
    gcsSource: {uris: [gcsSourceUri]},
  };
  const outputConfig = {
    predictionsFormat: 'jsonl',
    gcsDestination: {outputUriPrefix: gcsDestinationOutputUriPrefix},
  };
  const batchPredictionJob = {
    displayName: batchPredictionDisplayName,
    model: modelName,
    modelParameters,
    inputConfig,
    outputConfig,
  };
  const request = {
    parent,
    batchPredictionJob,
  };

  // Create batch prediction job request
  const [response] = await jobServiceClient.createBatchPredictionJob(request);

  console.log('Create batch prediction job video classification response');
  console.log(`Name : ${response.name}`);
  console.log('Raw response:');
  console.log(JSON.stringify(response, null, 2));
}
createBatchPredictionJobVideoClassification();

Python

Bevor Sie dieses Beispiel anwenden, folgen Sie den Python-Einrichtungsschritten in der Vertex AI-Kurzanleitung zur Verwendung von Clientbibliotheken. Weitere Informationen finden Sie in der Referenzdokumentation zur Vertex AI Python API.

Richten Sie zur Authentifizierung bei Vertex AI Standardanmeldedaten für Anwendungen ein. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten.

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


def create_batch_prediction_job_video_classification_sample(
    project: str,
    display_name: str,
    model_name: str,
    gcs_source_uri: 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 = {
        "confidenceThreshold": 0.5,
        "maxPredictions": 10000,
        "segmentClassification": True,
        "shotClassification": True,
        "oneSecIntervalClassification": True,
    }
    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": "jsonl",
            "gcs_source": {"uris": [gcs_source_uri]},
        },
        "output_config": {
            "predictions_format": "jsonl",
            "gcs_destination": {"output_uri_prefix": gcs_destination_output_uri_prefix},
        },
    }
    parent = f"projects/{project}/locations/{location}"
    response = client.create_batch_prediction_job(
        parent=parent, batch_prediction_job=batch_prediction_job
    )
    print("response:", response)

Nächste Schritte

Informationen zum Suchen und Filtern von Codebeispielen für andere Google Cloud-Produkte finden Sie im Google Cloud-Beispielbrowser.