Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaPredictParamsVideoClassificationPredictionParams

Inherits:

Object

• Object
• Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaPredictParamsVideoClassificationPredictionParams

Includes:

Core::Hashable, Core::JsonObjectSupport

Defined in:

lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb

Overview

Prediction model parameters for Video Classification.

Instance Attribute Summary

• #confidence_threshold ⇒ Float

  The Model only returns predictions with at least this confidence score.

• #max_predictions ⇒ Fixnum

  The Model only returns up to that many top, by confidence score, predictions per instance.

• #one_sec_interval_classification ⇒ Boolean (also: #one_sec_interval_classification?)

  Set to true to request classification for a video at one-second intervals.

• #segment_classification ⇒ Boolean (also: #segment_classification?)

  Set to true to request segment-level classification.

• #shot_classification ⇒ Boolean (also: #shot_classification?)

  Set to true to request shot-level classification.

Instance Method Summary

• #initialize(**args) ⇒ GoogleCloudAiplatformV1SchemaPredictParamsVideoClassificationPredictionParams constructor

  A new instance of GoogleCloudAiplatformV1SchemaPredictParamsVideoClassificationPredictionParams.

• #update!(**args) ⇒ Object

  Update properties of this object.

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1SchemaPredictParamsVideoClassificationPredictionParams

Returns a new instance of GoogleCloudAiplatformV1SchemaPredictParamsVideoClassificationPredictionParams.

# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20802

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#confidence_threshold ⇒ Float

The Model only returns predictions with at least this confidence score. Default value is 0.0 Corresponds to the JSON property confidenceThreshold

Returns:

• (Float)

# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20762

def confidence_threshold
  @confidence_threshold
end

#max_predictions ⇒ Fixnum

The Model only returns up to that many top, by confidence score, predictions per instance. If this number is very high, the Model may return fewer predictions. Default value is 10,000. Corresponds to the JSON property maxPredictions

Returns:

• (Fixnum)

# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20769

def max_predictions
  @max_predictions
end

#one_sec_interval_classification ⇒ Boolean Also known as: one_sec_interval_classification?

Set to true to request classification for a video at one-second intervals. Vertex AI returns labels and their confidence scores for each second of the entire time segment of the video that user specified in the input WARNING: Model evaluation is not done for this classification type, the quality of it depends on the training data, but there are no metrics provided to describe that quality. Default value is false Corresponds to the JSON property oneSecIntervalClassification

Returns:

• (Boolean)

# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20779

def one_sec_interval_classification
  @one_sec_interval_classification
end

#segment_classification ⇒ Boolean Also known as: segment_classification?

Set to true to request segment-level classification. Vertex AI returns labels and their confidence scores for the entire time segment of the video that user specified in the input instance. Default value is true Corresponds to the JSON property segmentClassification

Returns:

• (Boolean)

# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20787

def segment_classification
  @segment_classification
end

#shot_classification ⇒ Boolean Also known as: shot_classification?

Set to true to request shot-level classification. Vertex AI determines the boundaries for each camera shot in the entire time segment of the video that user specified in the input instance. Vertex AI then returns labels and their confidence scores for each detected shot, along with the start and end time of the shot. WARNING: Model evaluation is not done for this classification type, the quality of it depends on the training data, but there are no metrics provided to describe that quality. Default value is false Corresponds to the JSON property shotClassification

Returns:

• (Boolean)

# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20799

def shot_classification
  @shot_classification
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object

# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20807

def update!(**args)
  @confidence_threshold = args[:confidence_threshold] if args.key?(:confidence_threshold)
  @max_predictions = args[:max_predictions] if args.key?(:max_predictions)
  @one_sec_interval_classification = args[:one_sec_interval_classification] if args.key?(:one_sec_interval_classification)
  @segment_classification = args[:segment_classification] if args.key?(:segment_classification)
  @shot_classification = args[:shot_classification] if args.key?(:shot_classification)
end