Vision AI v1 API - Class VertexCustomConfig (1.0.0-beta01) 

public sealed class VertexCustomConfig : IMessage<VertexCustomConfig>, IEquatable<VertexCustomConfig>, IDeepCloneable<VertexCustomConfig>, IBufferMessage, IMessage

Reference documentation and code samples for the Vision AI v1 API class VertexCustomConfig.

Message describing VertexCustomConfig.

Inheritance

object > VertexCustomConfig

Namespace

Google.Cloud.VisionAI.V1

Assembly

Google.Cloud.VisionAI.V1.dll

Constructors

VertexCustomConfig()

public VertexCustomConfig()

VertexCustomConfig(VertexCustomConfig)

public VertexCustomConfig(VertexCustomConfig other)
Parameter
Name Description
other VertexCustomConfig

Properties

AttachApplicationMetadata

public bool AttachApplicationMetadata { get; set; }

If true, the prediction request received by custom model will also contain metadata with the following schema: 'appPlatformMetadata': { 'ingestionTime': DOUBLE; (UNIX timestamp) 'application': STRING; 'instanceId': STRING; 'node': STRING; 'processor': STRING; }

Property Value
Type Description
bool

DedicatedResources

public DedicatedResources DedicatedResources { get; set; }

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

Property Value
Type Description
DedicatedResources

DynamicConfigInputTopic

public string DynamicConfigInputTopic { get; set; }

Optional. By setting the configuration_input_topic, processor will subscribe to given topic, only pub/sub topic is supported now. Example channel: //pubsub.googleapis.com/projects/visionai-testing-stable/topics/test-topic message schema should be: message Message { // The ID of the stream that associates with the application instance. string stream_id = 1; // The target fps. By default, the custom processor will not send any data to the Vertex Prediction container. Note that once the dynamic_config_input_topic is set, max_prediction_fps will not work and be preceded by the fps set inside the topic. int32 fps = 2; }

Property Value
Type Description
string

HasDynamicConfigInputTopic

public bool HasDynamicConfigInputTopic { get; }

Gets whether the "dynamic_config_input_topic" field is set

Property Value
Type Description
bool

MaxPredictionFps

public int MaxPredictionFps { get; set; }

The max prediction frame per second. This attribute sets how fast the operator sends prediction requests to Vertex AI endpoint. Default value is 0, which means there is no max prediction fps limit. The operator sends prediction requests at input fps.

Property Value
Type Description
int

PostProcessingCloudFunction

public string PostProcessingCloudFunction { get; set; }

If not empty, the prediction result will be sent to the specified cloud function for post processing.

  • The cloud function will receive AppPlatformCloudFunctionRequest where the annotations field will be the json format of proto PredictResponse.
  • The cloud function should return AppPlatformCloudFunctionResponse with PredictResponse stored in the annotations field.
  • To drop the prediction output, simply clear the payload field in the returned AppPlatformCloudFunctionResponse.
Property Value
Type Description
string