Skip to content
AWS for Query.Farm

aws.rekognition.describe_project_versions

Example SQL Queries

SELECT * FROM
aws.rekognition.describe_project_versions
WHERE
"project_arn" = 'VALUE';

Description

Lists and describes the versions of an Amazon Rekognition project. You can specify up to 10 model or adapter versions in ProjectVersionArns. If you don't specify a value, descriptions for all model/adapter versions in the project are returned.

This operation requires permissions to perform the rekognition:DescribeProjectVersions action.

Table Definition

Column NameColumn Data Type
project_arn Required Input Column

The Amazon Resource Name (ARN) of the project that contains the model/adapter you want to describe.

VARCHAR
version_names Input Column

A list of model or project version names that you want to describe. You can add up to 10 model or project version names to the list. If you don't specify a value, all project version descriptions are returned. A version name is part of a project version ARN. For example, my-model.2020-01-21T09.10.15 is the version name in the following ARN. arn:aws:rekognition:us-east-1:123456789012:project/getting-started/version/my-model.2020-01-21T09.10.15/1234567890123.

VARCHAR[]
Show child fields
version_names[]
_aws_profile Input Column

The AWS profile defines the AWS identity used. It can be defined via credentials or by assuming a IAM role.

STRUCT(
    "type" VARCHAR,
    "name" VARCHAR,
    "account_id" VARCHAR,
    "via_profile_name" VARCHAR,
    "assumed_role_arn" VARCHAR,
    "organization" STRUCT(
        "account_name" VARCHAR,
        "id" VARCHAR,
        "tags" STRUCT(
            "key" VARCHAR,
            "value" VARCHAR
        )[],
        "master_account" STRUCT(
            "id" VARCHAR,
            "email" VARCHAR
        ),
        "parents" STRUCT(
            "type" VARCHAR,
            "id" VARCHAR,
            "name" VARCHAR,
            "tags" STRUCT(
                "key" VARCHAR,
                "value" VARCHAR
            )[]
        )[]
    )
)
Show child fields
_aws_profile.account_id

The AWS account id

_aws_profile.assumed_role_arn

The ARN of the assumed role

_aws_profile.name

The unique name of the profile.

_aws_profile.organization

Information about this profile's membership in the AWS organization.

Show child fields
_aws_profile.organization.account_name

The name of account speciifed by the organization

_aws_profile.organization.id

The organization id

_aws_profile.organization.master_account
Show child fields
_aws_profile.organization.master_account.email

The organization master account email address

_aws_profile.organization.master_account.id

The organization master account id

_aws_profile.organization.parents[]
Show child fields
_aws_profile.organization.parents[].id

The id of the parent

_aws_profile.organization.parents[].name

The name of the parent

_aws_profile.organization.parents[].tags[]
Show child fields
_aws_profile.organization.parents[].tags[].key
_aws_profile.organization.parents[].tags[].value
_aws_profile.organization.parents[].type

The type of parent can be an organization unit or a root

_aws_profile.organization.tags[]
Show child fields
_aws_profile.organization.tags[].key
_aws_profile.organization.tags[].value
_aws_profile.type

The type of profile, either 'credentials' or 'assumed_role'

_aws_profile.via_profile_name

This IAM role for this profile is assumed by first utilizing another profile with this name to obtain credentials.

_aws_region Input Column

The AWS region to use.

VARCHAR
base_model_version

The base detection model version used to create the project version.

VARCHAR
billable_training_time_in_seconds

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.

BIGINT
creation_timestamp

The Unix datetime for the date and time that training started.

TIMESTAMP_S
evaluation_result

The training results. EvaluationResult is only returned if training is successful.

STRUCT(
    "f1_score" DOUBLE,
    "summary" STRUCT(
        "s3_object" STRUCT(
            "bucket" VARCHAR,
            "name" VARCHAR,
            "version" VARCHAR
        )
    )
)
Show child fields
evaluation_result.f1_score

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.

evaluation_result.summary

The S3 bucket that contains the training summary.

Show child fields
evaluation_result.summary.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
evaluation_result.summary.s3_object.bucket

Name of the S3 bucket.

evaluation_result.summary.s3_object.name

S3 object key name.

evaluation_result.summary.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

feature

The feature that was customized.

VARCHAR
feature_config

Feature specific configuration that was applied during training.

STRUCT(
    "content_moderation" STRUCT(
        "confidence_threshold" DOUBLE
    )
)
Show child fields
feature_config.content_moderation

Configuration options for Custom Moderation training.

Show child fields
feature_config.content_moderation.confidence_threshold

The confidence level you plan to use to identify if unsafe content is present during inference.

kms_key_id

The identifer for the AWS Key Management Service key (AWS KMS key) that was used to encrypt the model during training. 

VARCHAR
manifest_summary

The location of the summary manifest. The summary manifest provides aggregate data validation results for the training and test datasets.

STRUCT(
    "s3_object" STRUCT(
        "bucket" VARCHAR,
        "name" VARCHAR,
        "version" VARCHAR
    )
)
Show child fields
manifest_summary.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
manifest_summary.s3_object.bucket

Name of the S3 bucket.

manifest_summary.s3_object.name

S3 object key name.

manifest_summary.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

max_inference_units

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.

BIGINT
min_inference_units

The minimum number of inference units used by the model. Applies only to Custom Labels projects. For more information, see StartProjectVersion.

BIGINT
output_config

The location where training results are saved.

STRUCT(
    "s3_bucket" VARCHAR,
    "s3_key_prefix" VARCHAR
)
Show child fields
output_config.s3_bucket

The S3 bucket where training output is placed.

output_config.s3_key_prefix

The prefix applied to the training output files.

project_version_arn

The Amazon Resource Name (ARN) of the project version. 

VARCHAR
source_project_version_arn

If the model version was copied from a different project, SourceProjectVersionArn contains the ARN of the source model version. 

VARCHAR
status

The current status of the model version.

VARCHAR
status_message

A descriptive message for an error or warning that occurred.

VARCHAR
testing_data_result

Contains information about the testing results.

STRUCT(
    "input" STRUCT(
        "assets" STRUCT(
            "ground_truth_manifest" STRUCT(
                "s3_object" STRUCT(
                    "bucket" VARCHAR,
                    "name" VARCHAR,
                    "version" VARCHAR
                )
            )
        )[],
        "auto_create" BOOLEAN
    ),
    "output" STRUCT(
        "assets" STRUCT(
            "ground_truth_manifest" STRUCT(
                "s3_object" STRUCT(
                    "bucket" VARCHAR,
                    "name" VARCHAR,
                    "version" VARCHAR
                )
            )
        )[],
        "auto_create" BOOLEAN
    ),
    "validation" STRUCT(
        "assets" STRUCT(
            "ground_truth_manifest" STRUCT(
                "s3_object" STRUCT(
                    "bucket" VARCHAR,
                    "name" VARCHAR,
                    "version" VARCHAR
                )
            )
        )[]
    )
)
Show child fields
testing_data_result.input

The testing dataset that was supplied for training.

Show child fields
testing_data_result.input.assets[]
Show child fields
testing_data_result.input.assets[].ground_truth_manifest

The S3 bucket that contains an Amazon Sagemaker Ground Truth format manifest file.

Show child fields
testing_data_result.input.assets[].ground_truth_manifest.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
testing_data_result.input.assets[].ground_truth_manifest.s3_object.bucket

Name of the S3 bucket.

testing_data_result.input.assets[].ground_truth_manifest.s3_object.name

S3 object key name.

testing_data_result.input.assets[].ground_truth_manifest.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

testing_data_result.input.auto_create

If specified, Rekognition splits training dataset to create a test dataset for the training job.

testing_data_result.output

The subset of the dataset that was actually tested. Some images (assets) might not be tested due to file formatting and other issues.

Show child fields
testing_data_result.output.assets[]
Show child fields
testing_data_result.output.assets[].ground_truth_manifest

The S3 bucket that contains an Amazon Sagemaker Ground Truth format manifest file.

Show child fields
testing_data_result.output.assets[].ground_truth_manifest.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
testing_data_result.output.assets[].ground_truth_manifest.s3_object.bucket

Name of the S3 bucket.

testing_data_result.output.assets[].ground_truth_manifest.s3_object.name

S3 object key name.

testing_data_result.output.assets[].ground_truth_manifest.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

testing_data_result.output.auto_create

If specified, Rekognition splits training dataset to create a test dataset for the training job.

testing_data_result.validation

The location of the data validation manifest. The data validation manifest is created for the test dataset during model training.

Show child fields
testing_data_result.validation.assets[]
Show child fields
testing_data_result.validation.assets[].ground_truth_manifest

The S3 bucket that contains an Amazon Sagemaker Ground Truth format manifest file.

Show child fields
testing_data_result.validation.assets[].ground_truth_manifest.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
testing_data_result.validation.assets[].ground_truth_manifest.s3_object.bucket

Name of the S3 bucket.

testing_data_result.validation.assets[].ground_truth_manifest.s3_object.name

S3 object key name.

testing_data_result.validation.assets[].ground_truth_manifest.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

training_data_result

Contains information about the training results.

STRUCT(
    "input" STRUCT(
        "assets" STRUCT(
            "ground_truth_manifest" STRUCT(
                "s3_object" STRUCT(
                    "bucket" VARCHAR,
                    "name" VARCHAR,
                    "version" VARCHAR
                )
            )
        )[]
    ),
    "output" STRUCT(
        "assets" STRUCT(
            "ground_truth_manifest" STRUCT(
                "s3_object" STRUCT(
                    "bucket" VARCHAR,
                    "name" VARCHAR,
                    "version" VARCHAR
                )
            )
        )[]
    ),
    "validation" STRUCT(
        "assets" STRUCT(
            "ground_truth_manifest" STRUCT(
                "s3_object" STRUCT(
                    "bucket" VARCHAR,
                    "name" VARCHAR,
                    "version" VARCHAR
                )
            )
        )[]
    )
)
Show child fields
training_data_result.input

The training data that you supplied.

Show child fields
training_data_result.input.assets[]
Show child fields
training_data_result.input.assets[].ground_truth_manifest

The S3 bucket that contains an Amazon Sagemaker Ground Truth format manifest file.

Show child fields
training_data_result.input.assets[].ground_truth_manifest.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
training_data_result.input.assets[].ground_truth_manifest.s3_object.bucket

Name of the S3 bucket.

training_data_result.input.assets[].ground_truth_manifest.s3_object.name

S3 object key name.

training_data_result.input.assets[].ground_truth_manifest.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

training_data_result.output

Reference to images (assets) that were actually used during training with trained model predictions.

Show child fields
training_data_result.output.assets[]
Show child fields
training_data_result.output.assets[].ground_truth_manifest

The S3 bucket that contains an Amazon Sagemaker Ground Truth format manifest file.

Show child fields
training_data_result.output.assets[].ground_truth_manifest.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
training_data_result.output.assets[].ground_truth_manifest.s3_object.bucket

Name of the S3 bucket.

training_data_result.output.assets[].ground_truth_manifest.s3_object.name

S3 object key name.

training_data_result.output.assets[].ground_truth_manifest.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

training_data_result.validation

A manifest that you supplied for training, with validation results for each line.

Show child fields
training_data_result.validation.assets[]
Show child fields
training_data_result.validation.assets[].ground_truth_manifest

The S3 bucket that contains an Amazon Sagemaker Ground Truth format manifest file.

Show child fields
training_data_result.validation.assets[].ground_truth_manifest.s3_object

Provides the S3 bucket name and object name.

The region for the S3 bucket containing the S3 object must match the region you use for Amazon Rekognition operations.

For Amazon Rekognition to process an S3 object, the user must have permission to access the S3 object. For more information, see How Amazon Rekognition works with IAM in the Amazon Rekognition Developer Guide.

Show child fields
training_data_result.validation.assets[].ground_truth_manifest.s3_object.bucket

Name of the S3 bucket.

training_data_result.validation.assets[].ground_truth_manifest.s3_object.name

S3 object key name.

training_data_result.validation.assets[].ground_truth_manifest.s3_object.version

If the bucket is versioning enabled, you can specify the object version.

training_end_timestamp

The Unix date and time that training of the model ended.

TIMESTAMP_S
version_description

A user-provided description of the project version.

VARCHAR