本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

# 使用陰影變體測試模型
<a name="model-shadow-deployment"></a>

 您可以使用 SageMaker AI Model Shadow Deployments 建立長時間執行的陰影變體，以驗證模型服務堆疊的任何新候選元件，然後再將其提升至生產環境。下圖顯示更詳細的陰影收體運作情形。

![陰影變體的詳細資訊。](http://docs.aws.amazon.com/zh_tw/sagemaker/latest/dg/images/juxtaposer/shadow-variant.png)


## 部署陰影變體
<a name="model-shadow-deployment-deploy"></a>

 下列程式碼範例示範如何以程式設計方式部署陰影變體。請將範例中的{{使用者預留位置文字}}取代為您自己的資訊。

1.  建立兩個 SageMaker AI 模型：一個用於生產變體，另一個用於陰影變體。

   ```
   import boto3
   from sagemaker import get_execution_role, Session
                   
   aws_region = "{{aws-region}}"
   
   boto_session = boto3.Session(region_name=aws_region)
   sagemaker_client = boto_session.client("sagemaker")
   
   role = get_execution_role()
   
   bucket = Session(boto_session).default_bucket()
   
   model_name1 = "{{name-of-your-first-model}}"
   model_name2 = "{{name-of-your-second-model}}"
   
   sagemaker_client.create_model(
       ModelName = model_name1,
       ExecutionRoleArn = role,
       Containers=[
           {
               "Image": "{{ecr-image-uri-for-first-model}}",
               "ModelDataUrl": "{{s3-location-of-trained-first-model}}" 
           }
       ]
   )
   
   sagemaker_client.create_model(
       ModelName = model_name2,
       ExecutionRoleArn = role,
       Containers=[
           {
               "Image": "{{ecr-image-uri-for-second-model}}",
               "ModelDataUrl": "{{s3-location-of-trained-second-model}}" 
           }
       ]
   )
   ```

1.  建立端點組態。在組態中指定生產和陰影變體。

   ```
   endpoint_config_name = {{name-of-your-endpoint-config}}
   
   create_endpoint_config_response = sagemaker_client.create_endpoint_config(
       EndpointConfigName=endpoint_config_name,
       ProductionVariants=[
           {
               "VariantName": {{name-of-your-production-variant}},
               "ModelName": model_name1,
               "InstanceType": {{"ml.m5.xlarge"}},
               "InitialInstanceCount": {{1}},
               "InitialVariantWeight": {{1}},
           }
       ],
       ShadowProductionVariants=[
           {
               "VariantName": {{name-of-your-shadow-variant}},
               "ModelName": model_name2,
               "InstanceType": {{"ml.m5.xlarge"}},
               "InitialInstanceCount": {{1}},
               "InitialVariantWeight": {{1}},
           }
      ]
   )
   ```

1. 建立端點。

   ```
   create_endpoint_response = sm.create_endpoint(
       EndpointName={{name-of-your-endpoint}},
       EndpointConfigName=endpoint_config_name,
   )
   ```