Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaModelevaluationMetricsVideoActionMetrics

Inherits:
Object
  • Object
show all
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

The Evaluation metrics given a specific precision_window_length.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1SchemaModelevaluationMetricsVideoActionMetrics

Returns a new instance of GoogleCloudAiplatformV1SchemaModelevaluationMetricsVideoActionMetrics.



20050
20051
20052
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20050

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

Instance Attribute Details

#confidence_metricsArray<Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaModelevaluationMetricsVideoActionMetricsConfidenceMetrics>

Metrics for each label-match confidence_threshold from 0.05,0.10,...,0.95,0.96, 0.97,0.98,0.99. Corresponds to the JSON property confidenceMetrics



20035
20036
20037
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20035

def confidence_metrics
  @confidence_metrics
end

#mean_average_precisionFloat

The mean average precision. Corresponds to the JSON property meanAveragePrecision

Returns:

  • (Float)


20040
20041
20042
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20040

def mean_average_precision
  @mean_average_precision
end

#precision_window_lengthString

This VideoActionMetrics is calculated based on this prediction window length. If the predicted action's timestamp is inside the time window whose center is the ground truth action's timestamp with this specific length, the prediction result is treated as a true positive. Corresponds to the JSON property precisionWindowLength

Returns:

  • (String)


20048
20049
20050
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20048

def precision_window_length
  @precision_window_length
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



20055
20056
20057
20058
20059
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 20055

def update!(**args)
  @confidence_metrics = args[:confidence_metrics] if args.key?(:confidence_metrics)
  @mean_average_precision = args[:mean_average_precision] if args.key?(:mean_average_precision)
  @precision_window_length = args[:precision_window_length] if args.key?(:precision_window_length)
end