| Package | Description |
|---|---|
| com.amazonaws.services.sagemaker.model |
| Modifier and Type | Method and Description |
|---|---|
RecommendationMetrics |
RecommendationMetrics.clone() |
RecommendationMetrics |
InferenceRecommendation.getMetrics()
The metrics used to decide what recommendation to make.
|
RecommendationMetrics |
RecommendationMetrics.withCostPerHour(Float costPerHour)
Defines the cost per hour for the instance.
|
RecommendationMetrics |
RecommendationMetrics.withCostPerInference(Float costPerInference)
Defines the cost per inference for the instance .
|
RecommendationMetrics |
RecommendationMetrics.withMaxInvocations(Integer maxInvocations)
The expected maximum number of requests per minute for the instance.
|
RecommendationMetrics |
RecommendationMetrics.withModelLatency(Integer modelLatency)
The expected model latency at maximum invocation per minute for the instance.
|
| Modifier and Type | Method and Description |
|---|---|
void |
InferenceRecommendation.setMetrics(RecommendationMetrics metrics)
The metrics used to decide what recommendation to make.
|
InferenceRecommendation |
InferenceRecommendation.withMetrics(RecommendationMetrics metrics)
The metrics used to decide what recommendation to make.
|
Copyright © 2022. All rights reserved.