MachineLearningBatchDeploymentProperties Class
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.
Batch inference settings per deployment.
public class MachineLearningBatchDeploymentProperties : Azure.ResourceManager.MachineLearning.Models.MachineLearningEndpointDeploymentProperties, System.ClientModel.Primitives.IJsonModel<Azure.ResourceManager.MachineLearning.Models.MachineLearningBatchDeploymentProperties>, System.ClientModel.Primitives.IPersistableModel<Azure.ResourceManager.MachineLearning.Models.MachineLearningBatchDeploymentProperties>public class MachineLearningBatchDeploymentProperties : Azure.ResourceManager.MachineLearning.Models.MachineLearningEndpointDeploymentPropertiestype MachineLearningBatchDeploymentProperties = class
inherit MachineLearningEndpointDeploymentProperties
interface IJsonModel<MachineLearningBatchDeploymentProperties>
interface IPersistableModel<MachineLearningBatchDeploymentProperties>type MachineLearningBatchDeploymentProperties = class
inherit MachineLearningEndpointDeploymentPropertiesPublic Class MachineLearningBatchDeploymentProperties
Inherits MachineLearningEndpointDeploymentProperties
Implements IJsonModel(Of MachineLearningBatchDeploymentProperties), IPersistableModel(Of MachineLearningBatchDeploymentProperties)Public Class MachineLearningBatchDeploymentProperties
Inherits MachineLearningEndpointDeploymentProperties- Inheritance
- Implements
Constructors
| MachineLearningBatchDeploymentProperties() |
Initializes a new instance of MachineLearningBatchDeploymentProperties. |
Properties
| CodeConfiguration |
Code configuration for the endpoint deployment. (Inherited from MachineLearningEndpointDeploymentProperties) |
| Compute |
Compute target for batch inference operation. |
| DeploymentConfiguration |
Properties relevant to different deployment types. Please note BatchDeploymentConfiguration is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include BatchPipelineComponentDeploymentConfiguration. |
| Description |
Description of the endpoint deployment. (Inherited from MachineLearningEndpointDeploymentProperties) |
| EnvironmentId |
ARM resource ID or AssetId of the environment specification for the endpoint deployment. (Inherited from MachineLearningEndpointDeploymentProperties) |
| EnvironmentVariables |
Environment variables configuration for the deployment. (Inherited from MachineLearningEndpointDeploymentProperties) |
| ErrorThreshold |
Error threshold, if the error count for the entire input goes above this value, the batch inference will be aborted. Range is [-1, int.MaxValue]. For FileDataset, this value is the count of file failures. For TabularDataset, this value is the count of record failures. If set to -1 (the lower bound), all failures during batch inference will be ignored. |
| LoggingLevel |
Logging level for batch inference operation. |
| MaxConcurrencyPerInstance |
Indicates maximum number of parallelism per instance. |
| MiniBatchSize |
Size of the mini-batch passed to each batch invocation. For FileDataset, this is the number of files per mini-batch. For TabularDataset, this is the size of the records in bytes, per mini-batch. |
| Model |
Reference to the model asset for the endpoint deployment. Please note MachineLearningAssetReferenceBase is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include MachineLearningDataPathAssetReference, MachineLearningIdAssetReference and MachineLearningOutputPathAssetReference. |
| OutputAction |
Indicates how the output will be organized. |
| OutputFileName |
Customized output file name for append_row output action. |
| Properties |
Property dictionary. Properties can be added, but not removed or altered. (Inherited from MachineLearningEndpointDeploymentProperties) |
| ProvisioningState |
Provisioning state for the endpoint deployment. |
| Resources |
Indicates compute configuration for the job. If not provided, will default to the defaults defined in ResourceConfiguration. |
| RetrySettings |
Retry Settings for the batch inference operation. If not provided, will default to the defaults defined in BatchRetrySettings. |
