Creates a new version of Amazon Rekognition project (like a Custom Labels model or a custom adapter) and begins training. Models and adapters are managed as part of a Rekognition project. The response from CreateProjectVersion is an Amazon Resource Name (ARN) for the project version.
The FeatureConfig operation argument allows you to configure specific model or adapter settings. You can provide a description to the project version by using the VersionDescription argment. Training can take a while to complete. You can get the current status by calling DescribeProjectVersions. Training completed successfully if the value of the Status field is TRAINING_COMPLETED. Once training has successfully completed, call DescribeProjectVersions to get the training results and evaluate the model.
This operation requires permissions to perform the rekognition:CreateProjectVersion action.
The following applies only to projects with Amazon Rekognition Custom Labels as the chosen feature:
You can train a model in a project that doesn't have associated datasets by specifying manifest files in the TrainingData and TestingData fields.
If you open the console after training a model with manifest files, Amazon Rekognition Custom Labels creates the datasets for you using the most recent manifest files. You can no longer train a model version for the project by specifying manifest files.
Instead of training with a project without associated datasets, we recommend that you use the manifest files to create training and test datasets for the project.
Parameters:
-
project_arn
(ProjectArn)
–
The ARN of the Amazon Rekognition project that will manage the project version you want to train.
-
version_name
(VersionName)
–
A name for the version of the project version. This value must be unique.
-
output_config
(OutputConfig)
–
The Amazon S3 bucket location to store the results of training. The bucket can be any S3 bucket in your AWS account. You need s3:PutObject permission on the bucket.
-
training_data
(Optional[TrainingData], default:
None
)
–
Specifies an external manifest that the services uses to train the project version. If you specify TrainingData you must also specify TestingData. The project must not have any associated datasets.
-
testing_data
(Optional[TestingData], default:
None
)
–
Specifies an external manifest that the service uses to test the project version. If you specify TestingData you must also specify TrainingData. The project must not have any associated datasets.
-
tags
(Optional[TagMap], default:
None
)
–
A set of tags (key-value pairs) that you want to attach to the project version.
-
kms_key_id
(Optional[KmsKeyId], default:
None
)
–
The identifier for your AWS Key Management Service key (AWS KMS key). You can supply the Amazon Resource Name (ARN) of your KMS key, the ID of your KMS key, an alias for your KMS key, or an alias ARN. The key is used to encrypt training images, test images, and manifest files copied into the service for the project version. Your source images are unaffected. The key is also used to encrypt training results and manifest files written to the output Amazon S3 bucket (OutputConfig).
If you choose to use your own KMS key, you need the following permissions on the KMS key.
-
kms:CreateGrant
-
kms:DescribeKey
-
kms:GenerateDataKey
-
kms:Decrypt
If you don't specify a value for KmsKeyId, images copied into the service are encrypted using a key that AWS owns and manages.
-
version_description
(Optional[VersionDescription], default:
None
)
–
A description applied to the project version being created.
-
feature_config
(Optional[CustomizationFeatureConfig], default:
None
)
–
Feature-specific configuration of the training job. If the job configuration does not match the feature type associated with the project, an InvalidParameterException is returned.
Raises:
-
AccessDeniedException
–
You are not authorized to perform the action.
-
InternalServerError
–
Amazon Rekognition experienced a service issue. Try your call again.
-
InvalidParameterException
–
Input parameter violated a constraint. Validate your parameter before calling the API operation again.
-
LimitExceededException
–
An Amazon Rekognition service limit was exceeded. For example, if you start too many jobs concurrently, subsequent calls to start operations (ex: StartLabelDetection) will raise a LimitExceededException exception (HTTP status code: 400) until the number of concurrently running jobs is below the Amazon Rekognition service limit.
-
ProvisionedThroughputExceededException
–
The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon Rekognition.
-
ResourceInUseException
–
The specified resource is already being used.
-
ResourceNotFoundException
–
The resource specified in the request cannot be found.
-
ServiceQuotaExceededException
–
The size of the collection exceeds the allowed limit. For more information, see Guidelines and quotas in Amazon Rekognition in the Amazon Rekognition Developer Guide.
-
ThrottlingException
–
Amazon Rekognition is temporarily unable to process the request. Try your call again.
-
UnknownServiceError
–
The service returned an error code this client does not model.
Examples:
To train an Amazon Rekognition Custom Labels model
Trains a version of an Amazon Rekognition Custom Labels model.
>>> client.create_project_version(project_arn='arn:aws:rekognition:us-east-1:111122223333:project/my-project/1690474772815', version_name='1', output_config={'S3Bucket': 'output_bucket', 'S3KeyPrefix': 'output_folder'})
Source code in docs_src/capo_rekognition/_services/rekognition.py
| def create_project_version(
self,
project_arn: "capo_rekognition.types.project_arn.ProjectArn",
version_name: "capo_rekognition.types.version_name.VersionName",
output_config: "capo_rekognition.types.output_config.OutputConfig",
*,
config_overrides: Optional[RekognitionClientConfig] = None,
training_data: Optional[
"capo_rekognition.types.training_data.TrainingData"
] = None,
testing_data: Optional[
"capo_rekognition.types.testing_data.TestingData"
] = None,
tags: Optional["capo_rekognition.types.tag_map.TagMap"] = None,
kms_key_id: Optional["capo_rekognition.types.kms_key_id.KmsKeyId"] = None,
version_description: Optional[
"capo_rekognition.types.version_description.VersionDescription"
] = None,
feature_config: Optional[
"capo_rekognition.types.customization_feature_config.CustomizationFeatureConfig"
] = None,
) -> "capo_rekognition.types.create_project_version_response.CreateProjectVersionResponse":
"""<p>Creates a new version of Amazon Rekognition project (like a Custom Labels model or a custom adapter) and begins training. Models and adapters are managed as part of a Rekognition project. The response from <code>CreateProjectVersion</code> is an Amazon Resource Name (ARN) for the project version. </p> <p>The FeatureConfig operation argument allows you to configure specific model or adapter settings. You can provide a description to the project version by using the VersionDescription argment. Training can take a while to complete. You can get the current status by calling <a>DescribeProjectVersions</a>. Training completed successfully if the value of the <code>Status</code> field is <code>TRAINING_COMPLETED</code>. Once training has successfully completed, call <a>DescribeProjectVersions</a> to get the training results and evaluate the model.</p> <p>This operation requires permissions to perform the <code>rekognition:CreateProjectVersion</code> action.</p> <note> <p> <i>The following applies only to projects with Amazon Rekognition Custom Labels as the chosen feature:</i> </p> <p>You can train a model in a project that doesn't have associated datasets by specifying manifest files in the <code>TrainingData</code> and <code>TestingData</code> fields. </p> <p>If you open the console after training a model with manifest files, Amazon Rekognition Custom Labels creates the datasets for you using the most recent manifest files. You can no longer train a model version for the project by specifying manifest files. </p> <p>Instead of training with a project without associated datasets, we recommend that you use the manifest files to create training and test datasets for the project.</p> </note> <p></p>
Args:
project_arn: <p>The ARN of the Amazon Rekognition project that will manage the project version you want to train.</p>
version_name: <p>A name for the version of the project version. This value must be unique.</p>
output_config: <p>The Amazon S3 bucket location to store the results of training. The bucket can be any S3 bucket in your AWS account. You need <code>s3:PutObject</code> permission on the bucket. </p>
training_data: <p>Specifies an external manifest that the services uses to train the project version. If you specify <code>TrainingData</code> you must also specify <code>TestingData</code>. The project must not have any associated datasets. </p>
testing_data: <p>Specifies an external manifest that the service uses to test the project version. If you specify <code>TestingData</code> you must also specify <code>TrainingData</code>. The project must not have any associated datasets.</p>
tags: <p> A set of tags (key-value pairs) that you want to attach to the project version. </p>
kms_key_id: <p>The identifier for your AWS Key Management Service key (AWS KMS key). You can supply the Amazon Resource Name (ARN) of your KMS key, the ID of your KMS key, an alias for your KMS key, or an alias ARN. The key is used to encrypt training images, test images, and manifest files copied into the service for the project version. Your source images are unaffected. The key is also used to encrypt training results and manifest files written to the output Amazon S3 bucket (<code>OutputConfig</code>).</p> <p>If you choose to use your own KMS key, you need the following permissions on the KMS key.</p> <ul> <li> <p>kms:CreateGrant</p> </li> <li> <p>kms:DescribeKey</p> </li> <li> <p>kms:GenerateDataKey</p> </li> <li> <p>kms:Decrypt</p> </li> </ul> <p>If you don't specify a value for <code>KmsKeyId</code>, images copied into the service are encrypted using a key that AWS owns and manages.</p>
version_description: <p>A description applied to the project version being created.</p>
feature_config: <p>Feature-specific configuration of the training job. If the job configuration does not match the feature type associated with the project, an InvalidParameterException is returned.</p>
Raises:
capo_rekognition.errors.access_denied_exception.AccessDeniedException: <p>You are not authorized to perform the action.</p>
capo_rekognition.errors.internal_server_error.InternalServerError: <p>Amazon Rekognition experienced a service issue. Try your call again.</p>
capo_rekognition.errors.invalid_parameter_exception.InvalidParameterException: <p>Input parameter violated a constraint. Validate your parameter before calling the API operation again.</p>
capo_rekognition.errors.limit_exceeded_exception.LimitExceededException: <p>An Amazon Rekognition service limit was exceeded. For example, if you start too many jobs concurrently, subsequent calls to start operations (ex: <code>StartLabelDetection</code>) will raise a <code>LimitExceededException</code> exception (HTTP status code: 400) until the number of concurrently running jobs is below the Amazon Rekognition service limit. </p>
capo_rekognition.errors.provisioned_throughput_exceeded_exception.ProvisionedThroughputExceededException: <p>The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon Rekognition.</p>
capo_rekognition.errors.resource_in_use_exception.ResourceInUseException: <p>The specified resource is already being used.</p>
capo_rekognition.errors.resource_not_found_exception.ResourceNotFoundException: <p>The resource specified in the request cannot be found.</p>
capo_rekognition.errors.service_quota_exceeded_exception.ServiceQuotaExceededException: <p></p> <p>The size of the collection exceeds the allowed limit. For more information, see Guidelines and quotas in Amazon Rekognition in the Amazon Rekognition Developer Guide. </p>
capo_rekognition.errors.throttling_exception.ThrottlingException: <p>Amazon Rekognition is temporarily unable to process the request. Try your call again.</p>
capo_rekognition.errors.UnknownServiceError: The service returned an error code this client does not model.
Examples:
To train an Amazon Rekognition Custom Labels model
Trains a version of an Amazon Rekognition Custom Labels model.
>>> client.create_project_version(project_arn='arn:aws:rekognition:us-east-1:111122223333:project/my-project/1690474772815', version_name='1', output_config={'S3Bucket': 'output_bucket', 'S3KeyPrefix': 'output_folder'})
"""
def _handler(
req: "OperationRequest[capo_rekognition.types.create_project_version_request.CreateProjectVersionRequest]",
) -> OperationResponse[
"capo_rekognition.types.create_project_version_response.CreateProjectVersionResponse"
]:
import capo_rekognition._operations.rekognition_service.create_project_version
output, http_response = (
capo_rekognition._operations.rekognition_service.create_project_version.create_project_version(
req.options, req.input
)
)
return OperationResponse(output=output, response=http_response)
interceptors_, options_ = self.operation_options(
config_overrides, OperationLogging("CreateProjectVersion")
)
input_: capo_rekognition.types.create_project_version_request.CreateProjectVersionRequest = {
"project_arn": project_arn,
"version_name": version_name,
"output_config": output_config,
}
if training_data is not None:
input_["training_data"] = training_data
if testing_data is not None:
input_["testing_data"] = testing_data
if tags is not None:
input_["tags"] = tags
if kms_key_id is not None:
input_["kms_key_id"] = kms_key_id
if version_description is not None:
input_["version_description"] = version_description
if feature_config is not None:
input_["feature_config"] = feature_config
response = execute_pipeline(
OperationRequest(input=input_, options=options_),
handler=_handler,
interceptors=list(interceptors_),
)
response.response.close()
return response.output
|