Class: Aws::SageMaker::Types::RecommendationMetrics

Inherits:

Struct

• Object
• Struct
• Aws::SageMaker::Types::RecommendationMetrics

Includes:

Aws::Structure

Defined in:

lib/aws-sdk-sagemaker/types.rb

Overview

The metrics of recommendations.

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[]

Instance Attribute Summary

• #cost_per_hour ⇒ Float

  Defines the cost per hour for the instance.

• #cost_per_inference ⇒ Float

  Defines the cost per inference for the instance .

• #cpu_utilization ⇒ Float

  The expected CPU utilization at maximum invocations per minute for the instance.

• #max_invocations ⇒ Integer

  The expected maximum number of requests per minute for the instance.

• #memory_utilization ⇒ Float

  The expected memory utilization at maximum invocations per minute for the instance.

• #model_latency ⇒ Integer

  The expected model latency at maximum invocation per minute for the instance.

• #model_setup_time ⇒ Integer

  The time it takes to launch new compute resources for a serverless endpoint.

Instance Attribute Details

#cost_per_hour ⇒ Float

Defines the cost per hour for the instance.

# File 'lib/aws-sdk-sagemaker/types.rb', line 49307

class RecommendationMetrics < Struct.new(
  :cost_per_hour,
  :cost_per_inference,
  :max_invocations,
  :model_latency,
  :cpu_utilization,
  :memory_utilization,
  :model_setup_time)
  SENSITIVE = []
  include Aws::Structure
end

#cost_per_inference ⇒ Float

Defines the cost per inference for the instance .

# File 'lib/aws-sdk-sagemaker/types.rb', line 49307

class RecommendationMetrics < Struct.new(
  :cost_per_hour,
  :cost_per_inference,
  :max_invocations,
  :model_latency,
  :cpu_utilization,
  :memory_utilization,
  :model_setup_time)
  SENSITIVE = []
  include Aws::Structure
end

#cpu_utilization ⇒ Float

The expected CPU utilization at maximum invocations per minute for the instance.

NaN indicates that the value is not available.

# File 'lib/aws-sdk-sagemaker/types.rb', line 49307

class RecommendationMetrics < Struct.new(
  :cost_per_hour,
  :cost_per_inference,
  :max_invocations,
  :model_latency,
  :cpu_utilization,
  :memory_utilization,
  :model_setup_time)
  SENSITIVE = []
  include Aws::Structure
end

#max_invocations ⇒ Integer

The expected maximum number of requests per minute for the instance.

# File 'lib/aws-sdk-sagemaker/types.rb', line 49307

class RecommendationMetrics < Struct.new(
  :cost_per_hour,
  :cost_per_inference,
  :max_invocations,
  :model_latency,
  :cpu_utilization,
  :memory_utilization,
  :model_setup_time)
  SENSITIVE = []
  include Aws::Structure
end

#memory_utilization ⇒ Float

The expected memory utilization at maximum invocations per minute for the instance.

NaN indicates that the value is not available.

# File 'lib/aws-sdk-sagemaker/types.rb', line 49307

class RecommendationMetrics < Struct.new(
  :cost_per_hour,
  :cost_per_inference,
  :max_invocations,
  :model_latency,
  :cpu_utilization,
  :memory_utilization,
  :model_setup_time)
  SENSITIVE = []
  include Aws::Structure
end

#model_latency ⇒ Integer

The expected model latency at maximum invocation per minute for the instance.

# File 'lib/aws-sdk-sagemaker/types.rb', line 49307

class RecommendationMetrics < Struct.new(
  :cost_per_hour,
  :cost_per_inference,
  :max_invocations,
  :model_latency,
  :cpu_utilization,
  :memory_utilization,
  :model_setup_time)
  SENSITIVE = []
  include Aws::Structure
end

#model_setup_time ⇒ Integer

The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container.

NaN indicates that the value is not available.

# File 'lib/aws-sdk-sagemaker/types.rb', line 49307

class RecommendationMetrics < Struct.new(
  :cost_per_hour,
  :cost_per_inference,
  :max_invocations,
  :model_latency,
  :cpu_utilization,
  :memory_utilization,
  :model_setup_time)
  SENSITIVE = []
  include Aws::Structure
end