Mendapatkan inferensi dari model pelacakan objek video

Halaman ini menunjukkan cara mendapatkan inferensi batch dari model pelacakan objek video menggunakan konsol Google Cloud atau Vertex AI API. Inferensi batch adalah permintaan asinkron. Anda meminta inferensi batch langsung dari resource model tanpa perlu men-deploy model ke endpoint.

Model video AutoML tidak mendukung inferensi online.

Mendapatkan inferensi batch

Untuk membuat permintaan inferensi batch, tentukan sumber input dan format output tempat Vertex AI menyimpan hasil inferensi.

Persyaratan data input

Input untuk permintaan batch menentukan item yang akan dikirim ke model Anda untuk inferensi. Inferensi batch untuk jenis model video AutoML menggunakan file JSON Lines untuk menentukan daftar video yang akan dibuat inferensinya, lalu menyimpan file JSON Lines tersebut di bucket Cloud Storage. Anda dapat menentukan Infinity untuk kolom timeSegmentEnd guna menentukan akhir video. Contoh berikut menunjukkan satu baris dalam file JSON Lines input.

{'content': 'gs://sourcebucket/datasets/videos/source_video.mp4', 'mimeType': 'video/mp4', 'timeSegmentStart': '0.0s', 'timeSegmentEnd': '2.366667s'}

Meminta inferensi batch

Untuk permintaan inferensi batch, Anda dapat menggunakan konsol Google Cloud atau Vertex AI API. Bergantung pada jumlah item input yang Anda kirimkan, tugas inferensi batch dapat memerlukan waktu beberapa saat untuk diselesaikan.

Google Cloud console

Gunakan konsol Google Cloud untuk meminta inferensi batch.

  1. Di konsol Google Cloud , di bagian Vertex AI, buka halaman Prediksi batch.

    Buka halaman Prediksi batch

  2. Klik Create untuk membuka jendela New batch predictions dan selesaikan langkah-langkah berikut:

    1. Masukkan nama untuk inferensi batch.
    2. Untuk Model name, pilih nama model yang akan digunakan untuk inferensi batch ini.
    3. Untuk Source path, tentukan lokasi Cloud Storage tempat file input JSON Lines Anda berada.
    4. Untuk Destination path, tentukan lokasi Cloud Storage tempat hasil inferensi batch disimpan. Format Output ditentukan oleh tujuan model Anda. Model AutoML untuk tujuan gambar menghasilkan file JSON Lines.

API

Gunakan Vertex AI API untuk mengirim permintaan inferensi batch.

REST

Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

  • LOCATION_ID: Region tempat Model disimpan dan tugas inferensi batch dijalankan. Misalnya, us-central1.
  • PROJECT_ID: Project ID Anda.
  • BATCH_JOB_NAME: Nama tampilan untuk tugas batch
  • MODEL_ID: ID yang digunakan oleh model untuk membuat inferensi
  • THRESHOLD_VALUE (opsional): Vertex AI hanya menampilkan inferensi yang memiliki skor keyakinan dengan nilai minimal ini. Dafaultnya adalah 0.0.
  • URI: Cloud Storage URI tempat file JSON Lines input Anda berada.
  • BUCKET: Bucket Cloud Storage Anda
  • PROJECT_NUMBER: Nomor project yang dibuat secara otomatis untuk project Anda

Metode HTTP dan URL: 

POST https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/batchPredictionJobs

Isi JSON permintaan: 

{
    "displayName": "BATCH_JOB_NAME",
    "model": "projects/PROJECT_ID/locations/LOCATION_ID/models/MODEL_ID",
    "modelParameters": {
      "confidenceThreshold": THRESHOLD_VALUE,
    },
    "inputConfig": {
        "instancesFormat": "jsonl",
        "gcsSource": {
            "uris": ["URI"],
        },
    },
    "outputConfig": {
        "predictionsFormat": "jsonl",
        "gcsDestination": {
            "outputUriPrefix": "OUTPUT_BUCKET",
        },
    },
}

Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

curl

Simpan isi permintaan dalam file bernama request.json, dan jalankan perintah berikut: 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/batchPredictionJobs"

PowerShell

Simpan isi permintaan dalam file bernama request.json, dan jalankan perintah berikut: 

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/batchPredictionJobs" | Select-Object -Expand Content

Anda akan menerima respons JSON yang mirip seperti berikut:

{
  "name": "projects/PROJECT_NUMBER/locations/us-central1/batchPredictionJobs/BATCH_JOB_ID",
  "displayName": "BATCH_JOB_NAME",
  "model": "projects/PROJECT_NUMBER/locations/us-central1/models/MODEL_ID",
  "inputConfig": {
    "instancesFormat": "jsonl",
    "gcsSource": {
      "uris": [
        "CONTENT"
      ]
    }
  },
  "outputConfig": {
    "predictionsFormat": "jsonl",
    "gcsDestination": {
      "outputUriPrefix": "BUCKET"
    }
  },
  "state": "JOB_STATE_PENDING",
  "createTime": "2020-05-30T02:58:44.341643Z",
  "updateTime": "2020-05-30T02:58:44.341643Z",
  "modelDisplayName": "MODEL_NAME",
  "modelObjective": "MODEL_OBJECTIVE"
}

Anda dapat melakukan polling untuk status tugas batch menggunakan BATCH_JOB_ID hingga state tugas menjadi JOB_STATE_SUCCEEDED.

Java

Sebelum mencoba contoh ini, ikuti petunjuk penyiapan Java di Panduan memulai Vertex AI menggunakan library klien. Untuk mengetahui informasi selengkapnya, lihat Dokumentasi referensi API Java Vertex AI.

Untuk melakukan autentikasi ke Vertex AI, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, lihat Menyiapkan autentikasi untuk lingkungan pengembangan lokal. 


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.VideoObjectTrackingPredictionParams;
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 CreateBatchPredictionJobVideoObjectTrackingSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String batchPredictionDisplayName = "YOUR_VIDEO_OBJECT_TRACKING_DISPLAY_NAME";
    String modelId = "YOUR_MODEL_ID";
    String gcsSourceUri =
        "gs://YOUR_GCS_SOURCE_BUCKET/path_to_your_video_source/[file.csv/file.jsonl]";
    String gcsDestinationOutputUriPrefix =
        "gs://YOUR_GCS_SOURCE_BUCKET/destination_output_uri_prefix/";
    String project = "YOUR_PROJECT_ID";
    batchPredictionJobVideoObjectTracking(
        batchPredictionDisplayName, modelId, gcsSourceUri, gcsDestinationOutputUriPrefix, project);
  }

  static void batchPredictionJobVideoObjectTracking(
      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 remaining background resources.
    try (JobServiceClient jobServiceClient = JobServiceClient.create(jobServiceSettings)) {
      String location = "us-central1";
      LocationName locationName = LocationName.of(project, location);
      ModelName modelName = ModelName.of(project, location, modelId);

      VideoObjectTrackingPredictionParams modelParamsObj =
          VideoObjectTrackingPredictionParams.newBuilder()
              .setConfidenceThreshold(((float) 0.5))
              .build();

      Value modelParameters = ValueConverter.toValue(modelParamsObj);

      GcsSource.Builder gcsSource = GcsSource.newBuilder();
      gcsSource.addUris(gcsSourceUri);
      InputConfig inputConfig =
          InputConfig.newBuilder().setInstancesFormat("jsonl").setGcsSource(gcsSource).build();

      GcsDestination gcsDestination =
          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 Object Tracking Response");
      System.out.format("\tName: %s\n", batchPredictionJobResponse.getName());
      System.out.format("\tDisplay Name: %s\n", batchPredictionJobResponse.getDisplayName());
      System.out.format("\tModel %s\n", batchPredictionJobResponse.getModel());
      System.out.format(
          "\tModel Parameters: %s\n", batchPredictionJobResponse.getModelParameters());

      System.out.format("\tState: %s\n", batchPredictionJobResponse.getState());
      System.out.format("\tCreate Time: %s\n", batchPredictionJobResponse.getCreateTime());
      System.out.format("\tStart Time: %s\n", batchPredictionJobResponse.getStartTime());
      System.out.format("\tEnd Time: %s\n", batchPredictionJobResponse.getEndTime());
      System.out.format("\tUpdate Time: %s\n", batchPredictionJobResponse.getUpdateTime());
      System.out.format("\tLabels: %s\n", batchPredictionJobResponse.getLabelsMap());

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

      GcsSource gcsSourceResponse = inputConfigResponse.getGcsSource();
      System.out.println("\t\tGcs Source");
      System.out.format("\t\t\tUris %s\n", gcsSourceResponse.getUrisList());

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

      OutputConfig outputConfigResponse = batchPredictionJobResponse.getOutputConfig();
      System.out.println("\tOutput Config");
      System.out.format(
          "\t\tPredictions Format: %s\n", outputConfigResponse.getPredictionsFormat());

      GcsDestination gcsDestinationResponse = outputConfigResponse.getGcsDestination();
      System.out.println("\t\tGcs Destination");
      System.out.format(
          "\t\t\tOutput Uri Prefix: %s\n", gcsDestinationResponse.getOutputUriPrefix());

      BigQueryDestination bigQueryDestination = outputConfigResponse.getBigqueryDestination();
      System.out.println("\t\tBig Query Destination");
      System.out.format("\t\t\tOutput Uri: %s\n", bigQueryDestination.getOutputUri());

      BatchDedicatedResources batchDedicatedResources =
          batchPredictionJobResponse.getDedicatedResources();
      System.out.println("\tBatch Dedicated Resources");
      System.out.format(
          "\t\tStarting Replica Count: %s\n", batchDedicatedResources.getStartingReplicaCount());
      System.out.format(
          "\t\tMax Replica Count: %s\n", batchDedicatedResources.getMaxReplicaCount());

      MachineSpec machineSpec = batchDedicatedResources.getMachineSpec();
      System.out.println("\t\tMachine Spec");
      System.out.format("\t\t\tMachine Type: %s\n", machineSpec.getMachineType());
      System.out.format("\t\t\tAccelerator Type: %s\n", machineSpec.getAcceleratorType());
      System.out.format("\t\t\tAccelerator Count: %s\n", machineSpec.getAcceleratorCount());

      ManualBatchTuningParameters manualBatchTuningParameters =
          batchPredictionJobResponse.getManualBatchTuningParameters();
      System.out.println("\tManual Batch Tuning Parameters");
      System.out.format("\t\tBatch Size: %s\n", manualBatchTuningParameters.getBatchSize());

      OutputInfo outputInfo = batchPredictionJobResponse.getOutputInfo();
      System.out.println("\tOutput Info");
      System.out.format("\t\tGcs Output Directory: %s\n", outputInfo.getGcsOutputDirectory());
      System.out.format("\t\tBigquery Output Dataset: %s\n", outputInfo.getBigqueryOutputDataset());

      Status status = batchPredictionJobResponse.getError();
      System.out.println("\tError");
      System.out.format("\t\tCode: %s\n", status.getCode());
      System.out.format("\t\tMessage: %s\n", status.getMessage());
      List<Any> details = status.getDetailsList();

      for (Status partialFailure : batchPredictionJobResponse.getPartialFailuresList()) {
        System.out.println("\tPartial Failure");
        System.out.format("\t\tCode: %s\n", partialFailure.getCode());
        System.out.format("\t\tMessage: %s\n", partialFailure.getMessage());
        List<Any> partialFailureDetailsList = partialFailure.getDetailsList();
      }

      ResourcesConsumed resourcesConsumed = batchPredictionJobResponse.getResourcesConsumed();
      System.out.println("\tResources Consumed");
      System.out.format("\t\tReplica Hours: %s\n", resourcesConsumed.getReplicaHours());

      CompletionStats completionStats = batchPredictionJobResponse.getCompletionStats();
      System.out.println("\tCompletion Stats");
      System.out.format("\t\tSuccessful Count: %s\n", completionStats.getSuccessfulCount());
      System.out.format("\t\tFailed Count: %s\n", completionStats.getFailedCount());
      System.out.format("\t\tIncomplete Count: %s\n", completionStats.getIncompleteCount());
    }
  }
}

Node.js

Sebelum mencoba contoh ini, ikuti petunjuk penyiapan Node.js di Panduan memulai Vertex AI menggunakan library klien. Untuk mengetahui informasi selengkapnya, lihat Dokumentasi referensi API Node.js Vertex AI.

Untuk melakukan autentikasi ke Vertex AI, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, lihat Menyiapkan autentikasi untuk lingkungan pengembangan lokal. 

/**
 * 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 createBatchPredictionJobVideoObjectTracking() {
  // 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.VideoObjectTrackingPredictionParams({
    confidenceThreshold: 0.5,
  });

  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 object tracking response');
  console.log(`Name : ${response.name}`);
  console.log('Raw response:');
  console.log(JSON.stringify(response, null, 2));
}
createBatchPredictionJobVideoObjectTracking();

Python

Untuk mempelajari cara menginstal atau mengupdate Vertex AI SDK untuk Python, lihat Menginstal Vertex AI SDK untuk Python. Untuk mengetahui informasi selengkapnya, lihat Dokumentasi referensi API Python. 

def create_batch_prediction_job_sample(
    project: str,
    location: str,
    model_resource_name: str,
    job_display_name: str,
    gcs_source: Union[str, Sequence[str]],
    gcs_destination: str,
    sync: bool = True,
):
    aiplatform.init(project=project, location=location)

    my_model = aiplatform.Model(model_resource_name)

    batch_prediction_job = my_model.batch_predict(
        job_display_name=job_display_name,
        gcs_source=gcs_source,
        gcs_destination_prefix=gcs_destination,
        sync=sync,
    )

    batch_prediction_job.wait()

    print(batch_prediction_job.display_name)
    print(batch_prediction_job.resource_name)
    print(batch_prediction_job.state)
    return batch_prediction_job

Mengambil hasil inferensi batch

Vertex AI mengirimkan output inferensi batch ke tujuan yang Anda tentukan.

Setelah tugas inferensi batch selesai, output inferensi akan disimpan di bucket Cloud Storage yang Anda tentukan dalam permintaan Anda.

Contoh hasil inferensi batch

Berikut ini contoh hasil inferensi batch dari model pelacakan objek video.

{
  "instance": {
   "content": "gs://bucket/video.mp4",
    "mimeType": "video/mp4",
    "timeSegmentStart": "1s",
    "timeSegmentEnd": "5s"
  }
  "prediction": [{
    "id": "1",
    "displayName": "cat",
    "timeSegmentStart": "1.2s",
    "timeSegmentEnd": "3.4s",
    "frames": [{
      "timeOffset": "1.2s",
      "xMin": 0.1,
      "xMax": 0.2,
      "yMin": 0.3,
      "yMax": 0.4
    }, {
      "timeOffset": "3.4s",
      "xMin": 0.2,
      "xMax": 0.3,
      "yMin": 0.4,
      "yMax": 0.5,
    }],
    "confidence": 0.7
  }, {
    "id": "1",
    "displayName": "cat",
    "timeSegmentStart": "4.8s",
    "timeSegmentEnd": "4.8s",
    "frames": [{
      "timeOffset": "4.8s",
      "xMin": 0.2,
      "xMax": 0.3,
      "yMin": 0.4,
      "yMax": 0.5,
    }],
    "confidence": 0.6
  }, {
    "id": "2",
    "displayName": "dog",
    "timeSegmentStart": "1.2s",
    "timeSegmentEnd": "3.4s",
    "frames": [{
      "timeOffset": "1.2s",
      "xMin": 0.1,
      "xMax": 0.2,
      "yMin": 0.3,
      "yMax": 0.4
    }, {
      "timeOffset": "3.4s",
      "xMin": 0.2,
      "xMax": 0.3,
      "yMin": 0.4,
      "yMax": 0.5,
    }],
    "confidence": 0.5
  }]
}

Sebelumnya
Evaluasi model
Berikutnya
Menafsirkan hasil