FormTrainingClient.StartTraining Method
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Trains a model from a collection of custom forms in an Azure Blob Storage container.
public virtual Azure.AI.FormRecognizer.Training.TrainingOperation StartTraining (Uri trainingFilesUri, bool useTrainingLabels, string modelName = default, Azure.AI.FormRecognizer.Training.TrainingOptions trainingOptions = default, System.Threading.CancellationToken cancellationToken = default);
abstract member StartTraining : Uri * bool * string * Azure.AI.FormRecognizer.Training.TrainingOptions * System.Threading.CancellationToken -> Azure.AI.FormRecognizer.Training.TrainingOperation
override this.StartTraining : Uri * bool * string * Azure.AI.FormRecognizer.Training.TrainingOptions * System.Threading.CancellationToken -> Azure.AI.FormRecognizer.Training.TrainingOperation
Public Overridable Function StartTraining (trainingFilesUri As Uri, useTrainingLabels As Boolean, Optional modelName As String = Nothing, Optional trainingOptions As TrainingOptions = Nothing, Optional cancellationToken As CancellationToken = Nothing) As TrainingOperation
Parameters
- trainingFilesUri
- Uri
An externally accessible Azure Blob Storage container URI pointing to the container that has your training files. Note that a container URI without SAS is accepted only when the container is public or has a managed identity configured. For more information on setting up a training data set, see this article.
- useTrainingLabels
- Boolean
If true
, corresponding labeled files must exist in the blob container. If false
, the model will be trained from forms only.
- modelName
- String
An optional, user-defined name to associate with the model. This property is only available for V2_1 and newer.
- trainingOptions
- TrainingOptions
A set of options available for configuring the training request. For example, set a filter to apply to the documents in the source path for training.
- cancellationToken
- CancellationToken
A CancellationToken controlling the request lifetime.
Returns
A TrainingOperation to wait on this long-running operation. Its Value upon successful completion will contain meta-data about the trained model.
Even if training fails, a model is created in the Form Recognizer account with an "invalid" status. A RequestFailedException will be raised containing the modelId to access this invalid model.