Creates a new version of a model and begins training
Creates a new version of a model and begins training. Models are managed
as part of an Amazon Rekognition Custom Labels project. You can specify
one training dataset and one testing dataset. The response from
create_project_version is an
Amazon Resource Name (ARN) for the version of the model.
Training takes a while to complete. You can get the current status by
calling
describe_project_versions.
Once training has successfully completed, call
describe_project_versions to
get the training results and evaluate the model.
After evaluating the model, you start the model by calling
start_project_version.
This operation requires permissions to perform the
rekognition:CreateProjectVersion action.
rekognition_create_project_version(ProjectArn, VersionName, OutputConfig, TrainingData, TestingData)
ProjectArn |
[required] The ARN of the Amazon Rekognition Custom Labels project that manages the model that you want to train. |
VersionName |
[required] A name for the version of the model. This value must be unique. |
OutputConfig |
[required] The Amazon S3 location to store the results of training. |
TrainingData |
[required] The dataset to use for training. |
TestingData |
[required] The dataset to use for testing. |
A list with the following syntax:
list( ProjectVersionArn = "string" )
svc$create_project_version(
ProjectArn = "string",
VersionName = "string",
OutputConfig = list(
S3Bucket = "string",
S3KeyPrefix = "string"
),
TrainingData = list(
Assets = list(
list(
GroundTruthManifest = list(
S3Object = list(
Bucket = "string",
Name = "string",
Version = "string"
)
)
)
)
),
TestingData = list(
Assets = list(
list(
GroundTruthManifest = list(
S3Object = list(
Bucket = "string",
Name = "string",
Version = "string"
)
)
)
),
AutoCreate = TRUE|FALSE
)
)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.