This product is not supported for your selected Datadog site. ().
이 페이지는 아직 영어로 제공되지 않습니다. 번역 작업 중입니다.
현재 번역 프로젝트에 대한 질문이나 피드백이 있으신 경우 언제든지 연락주시기 바랍니다.

aws_rekognition_project_version

account_id

Type: STRING

base_model_version

Type: STRING
Provider name: BaseModelVersion
Description: The base detection model version used to create the project version.

billable_training_time_in_seconds

Type: INT64
Provider name: BillableTrainingTimeInSeconds
Description: The duration, in seconds, that you were billed for a successful training of the model version. This value is only returned if the model version has been successfully trained.

creation_timestamp

Type: TIMESTAMP
Provider name: CreationTimestamp
Description: The Unix datetime for the date and time that training started.

evaluation_result

Type: STRUCT
Provider name: EvaluationResult
Description: The training results. EvaluationResult is only returned if training is successful.

  • f1_score
    Type: FLOAT
    Provider name: F1Score
    Description: The F1 score for the evaluation of all labels. The F1 score metric evaluates the overall precision and recall performance of the model as a single value. A higher value indicates better precision and recall performance. A lower score indicates that precision, recall, or both are performing poorly.
  • summary
    Type: STRUCT
    Provider name: Summary
    Description: The S3 bucket that contains the training summary.
    • s3_object
      Type: STRUCT
      Provider name: S3Object
      • bucket
        Type: STRING
        Provider name: Bucket
        Description: Name of the S3 bucket.
      • name
        Type: STRING
        Provider name: Name
        Description: S3 object key name.
      • version
        Type: STRING
        Provider name: Version
        Description: If the bucket is versioning enabled, you can specify the object version.

feature

Type: STRING
Provider name: Feature
Description: The feature that was customized.

feature_config

Type: STRUCT
Provider name: FeatureConfig
Description: Feature specific configuration that was applied during training.

  • content_moderation
    Type: STRUCT
    Provider name: ContentModeration
    Description: Configuration options for Custom Moderation training.
    • confidence_threshold
      Type: FLOAT
      Provider name: ConfidenceThreshold
      Description: The confidence level you plan to use to identify if unsafe content is present during inference.

kms_key_id

Type: STRING
Provider name: KmsKeyId
Description: The identifer for the AWS Key Management Service key (AWS KMS key) that was used to encrypt the model during training.

manifest_summary

Type: STRUCT
Provider name: ManifestSummary
Description: The location of the summary manifest. The summary manifest provides aggregate data validation results for the training and test datasets.

  • s3_object
    Type: STRUCT
    Provider name: S3Object
    • bucket
      Type: STRING
      Provider name: Bucket
      Description: Name of the S3 bucket.
    • name
      Type: STRING
      Provider name: Name
      Description: S3 object key name.
    • version
      Type: STRING
      Provider name: Version
      Description: If the bucket is versioning enabled, you can specify the object version.

max_inference_units

Type: INT32
Provider name: MaxInferenceUnits
Description: The maximum number of inference units Amazon Rekognition uses to auto-scale the model. Applies only to Custom Labels projects. For more information, see StartProjectVersion.

min_inference_units

Type: INT32
Provider name: MinInferenceUnits
Description: The minimum number of inference units used by the model. Applies only to Custom Labels projects. For more information, see StartProjectVersion.

output_config

Type: STRUCT
Provider name: OutputConfig
Description: The location where training results are saved.

  • s3_bucket
    Type: STRING
    Provider name: S3Bucket
    Description: The S3 bucket where training output is placed.
  • s3_key_prefix
    Type: STRING
    Provider name: S3KeyPrefix
    Description: The prefix applied to the training output files.

project_version_arn

Type: STRING
Provider name: ProjectVersionArn
Description: The Amazon Resource Name (ARN) of the project version.

source_project_version_arn

Type: STRING
Provider name: SourceProjectVersionArn
Description: If the model version was copied from a different project, SourceProjectVersionArn contains the ARN of the source model version.

status

Type: STRING
Provider name: Status
Description: The current status of the model version.

status_message

Type: STRING
Provider name: StatusMessage
Description: A descriptive message for an error or warning that occurred.

tags

Type: UNORDERED_LIST_STRING

testing_data_result

Type: STRUCT
Provider name: TestingDataResult
Description: Contains information about the testing results.

  • input
    Type: STRUCT
    Provider name: Input
    Description: The testing dataset that was supplied for training.
    • assets
      Type: UNORDERED_LIST_STRUCT
      Provider name: Assets
      Description: The assets used for testing.
      • ground_truth_manifest
        Type: STRUCT
        Provider name: GroundTruthManifest
        • s3_object
          Type: STRUCT
          Provider name: S3Object
          • bucket
            Type: STRING
            Provider name: Bucket
            Description: Name of the S3 bucket.
          • name
            Type: STRING
            Provider name: Name
            Description: S3 object key name.
          • version
            Type: STRING
            Provider name: Version
            Description: If the bucket is versioning enabled, you can specify the object version.
    • auto_create
      Type: BOOLEAN
      Provider name: AutoCreate
      Description: If specified, Rekognition splits training dataset to create a test dataset for the training job.
  • output
    Type: STRUCT
    Provider name: Output
    Description: The subset of the dataset that was actually tested. Some images (assets) might not be tested due to file formatting and other issues.
    • assets
      Type: UNORDERED_LIST_STRUCT
      Provider name: Assets
      Description: The assets used for testing.
      • ground_truth_manifest
        Type: STRUCT
        Provider name: GroundTruthManifest
        • s3_object
          Type: STRUCT
          Provider name: S3Object
          • bucket
            Type: STRING
            Provider name: Bucket
            Description: Name of the S3 bucket.
          • name
            Type: STRING
            Provider name: Name
            Description: S3 object key name.
          • version
            Type: STRING
            Provider name: Version
            Description: If the bucket is versioning enabled, you can specify the object version.
    • auto_create
      Type: BOOLEAN
      Provider name: AutoCreate
      Description: If specified, Rekognition splits training dataset to create a test dataset for the training job.
  • validation
    Type: STRUCT
    Provider name: Validation
    Description: The location of the data validation manifest. The data validation manifest is created for the test dataset during model training.
    • assets
      Type: UNORDERED_LIST_STRUCT
      Provider name: Assets
      Description: The assets that comprise the validation data.
      • ground_truth_manifest
        Type: STRUCT
        Provider name: GroundTruthManifest
        • s3_object
          Type: STRUCT
          Provider name: S3Object
          • bucket
            Type: STRING
            Provider name: Bucket
            Description: Name of the S3 bucket.
          • name
            Type: STRING
            Provider name: Name
            Description: S3 object key name.
          • version
            Type: STRING
            Provider name: Version
            Description: If the bucket is versioning enabled, you can specify the object version.

training_data_result

Type: STRUCT
Provider name: TrainingDataResult
Description: Contains information about the training results.

  • input
    Type: STRUCT
    Provider name: Input
    Description: The training data that you supplied.
    • assets
      Type: UNORDERED_LIST_STRUCT
      Provider name: Assets
      Description: A manifest file that contains references to the training images and ground-truth annotations.
      • ground_truth_manifest
        Type: STRUCT
        Provider name: GroundTruthManifest
        • s3_object
          Type: STRUCT
          Provider name: S3Object
          • bucket
            Type: STRING
            Provider name: Bucket
            Description: Name of the S3 bucket.
          • name
            Type: STRING
            Provider name: Name
            Description: S3 object key name.
          • version
            Type: STRING
            Provider name: Version
            Description: If the bucket is versioning enabled, you can specify the object version.
  • output
    Type: STRUCT
    Provider name: Output
    Description: Reference to images (assets) that were actually used during training with trained model predictions.
    • assets
      Type: UNORDERED_LIST_STRUCT
      Provider name: Assets
      Description: A manifest file that contains references to the training images and ground-truth annotations.
      • ground_truth_manifest
        Type: STRUCT
        Provider name: GroundTruthManifest
        • s3_object
          Type: STRUCT
          Provider name: S3Object
          • bucket
            Type: STRING
            Provider name: Bucket
            Description: Name of the S3 bucket.
          • name
            Type: STRING
            Provider name: Name
            Description: S3 object key name.
          • version
            Type: STRING
            Provider name: Version
            Description: If the bucket is versioning enabled, you can specify the object version.
  • validation
    Type: STRUCT
    Provider name: Validation
    Description: A manifest that you supplied for training, with validation results for each line.
    • assets
      Type: UNORDERED_LIST_STRUCT
      Provider name: Assets
      Description: The assets that comprise the validation data.
      • ground_truth_manifest
        Type: STRUCT
        Provider name: GroundTruthManifest
        • s3_object
          Type: STRUCT
          Provider name: S3Object
          • bucket
            Type: STRING
            Provider name: Bucket
            Description: Name of the S3 bucket.
          • name
            Type: STRING
            Provider name: Name
            Description: S3 object key name.
          • version
            Type: STRING
            Provider name: Version
            Description: If the bucket is versioning enabled, you can specify the object version.

training_end_timestamp

Type: TIMESTAMP
Provider name: TrainingEndTimestamp
Description: The Unix date and time that training of the model ended.

version_description

Type: STRING
Provider name: VersionDescription
Description: A user-provided description of the project version.