Merge pull request #77494 from j-martens/patch-481

Update how-to-deploy-and-where.md

Author: GitHubber17

articles/machine-learning/service/how-to-deploy-and-where.md

@@ -43,45 +43,45 @@ For more information on the concepts involved in the deployment workflow, see [M
 
 - The [Azure CLI extension for Machine Learning service](reference-azure-machine-learning-cli.md), or the [Azure Machine Learning Python SDK](https://aka.ms/aml-sdk).
 
-## <a id="registermodel"></a> Register ML models
+## <a id="registermodel"></a> Register your model
 
 Register your machine learning models in your Azure Machine Learning workspace. The model can come from Azure Machine Learning or can come from somewhere else. The following examples demonstrate how to register a model from file:
 
 ### Register a model from an Experiment Run
 
-**Scikit-Learn example with the CLI**
-```azurecli-interactive
-az ml model register -n sklearn_mnist  --asset-path outputs/sklearn_mnist_model.pkl  --experiment-name myexperiment
-```
-**Using the SDK**
-```python
-model = run.register_model(model_name='sklearn_mnist', model_path='outputs/sklearn_mnist_model.pkl')
-print(model.name, model.id, model.version, sep='\t')
-```
++ **Scikit-Learn example using the SDK**
+  ```python
+  model = run.register_model(model_name='sklearn_mnist', model_path='outputs/sklearn_mnist_model.pkl')
+  print(model.name, model.id, model.version, sep='\t')
+  ```
++ **Using the CLI**
+  ```azurecli-interactive
+  az ml model register -n sklearn_mnist  --asset-path outputs/sklearn_mnist_model.pkl  --experiment-name myexperiment
+  ```
 
 ### Register an externally created model
 
 [!INCLUDE [trusted models](../../../includes/machine-learning-service-trusted-model.md)]
 
 You can register an externally created model by providing a **local path** to the model. You can provide either a folder or a single file.
 
-**ONNX example with the Python SDK:**
-```python
-onnx_model_url = "https://www.cntk.ai/OnnxModels/mnist/opset_7/mnist.tar.gz"
-urllib.request.urlretrieve(onnx_model_url, filename="mnist.tar.gz")
-!tar xvzf mnist.tar.gz
-
-model = Model.register(workspace = ws,
-                       model_path ="mnist/model.onnx",
-                       model_name = "onnx_mnist",
-                       tags = {"onnx": "demo"},
-                       description = "MNIST image classification CNN from ONNX Model Zoo",)
-```
-
-**Using the CLI**
-```azurecli-interactive
-az ml model register -n onnx_mnist -p mnist/model.onnx
-```
++ **ONNX example with the Python SDK:**
+  ```python
+  onnx_model_url = "https://www.cntk.ai/OnnxModels/mnist/opset_7/mnist.tar.gz"
+  urllib.request.urlretrieve(onnx_model_url, filename="mnist.tar.gz")
+  !tar xvzf mnist.tar.gz
+  
+  model = Model.register(workspace = ws,
+                         model_path ="mnist/model.onnx",
+                         model_name = "onnx_mnist",
+                         tags = {"onnx": "demo"},
+                         description = "MNIST image classification CNN from ONNX Model Zoo",)
+  ```
+
++ **Using the CLI**
+  ```azurecli-interactive
+  az ml model register -n onnx_mnist -p mnist/model.onnx
+  ```
 
 **Time estimate**: Approximately 10 seconds.
 
@@ -218,79 +218,80 @@ The following sections demonstrate how to create the deployment configuration, a
 
 ## Deploy to target
 
-### <a id="local"></a> Deploy locally
+### <a id="local"></a> Local deployment
+
+To deploy locally, you need to have **Docker installed** on your local machine.
 
 The examples in this section use [deploy_from_image](https://docs.microsoft.com/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#deploy-from-model-workspace--name--models--image-config--deployment-config-none--deployment-target-none-), which requires you to register the model and image before doing a deployment. For more information on other deployment methods, see [deploy](https://docs.microsoft.com/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#deploy-workspace--name--model-paths--image-config--deployment-config-none--deployment-target-none-) and [deploy_from_model](https://docs.microsoft.com/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#deploy-from-model-workspace--name--models--image-config--deployment-config-none--deployment-target-none-).
 
-**To deploy locally, you need to have Docker installed on your local machine.**
 
-**Using the SDK**
++ **Using the SDK**
 
-```python
-deployment_config = LocalWebservice.deploy_configuration(port=8890)
-service = Model.deploy(ws, "myservice", [model], inference_config, deployment_config)
-service.wait_for_deployment(show_output = True)
-print(service.state)
-```
+  ```python
+  deployment_config = LocalWebservice.deploy_configuration(port=8890)
+  service = Model.deploy(ws, "myservice", [model], inference_config, deployment_config)
+  service.wait_for_deployment(show_output = True)
+  print(service.state)
+  ```
 
-**Using the CLI**
++ **Using the CLI**
 
-```azurecli-interactive
-az ml model deploy -m sklearn_mnist:1 -ic inferenceconfig.json -dc deploymentconfig.json
-```
+  ```azurecli-interactive
+  az ml model deploy -m sklearn_mnist:1 -ic inferenceconfig.json -dc deploymentconfig.json
+  ```
 
-### <a id="aci"></a> Deploy to Azure Container Instances (DEVTEST)
+### <a id="aci"></a> Azure Container Instances (DEVTEST)
 
 Use Azure Container Instances for deploying your models as a web service if one or more of the following conditions is true:
 - You need to quickly deploy and validate your model.
 - You are testing a model that is under development. 
 
 To see quota and region availability for ACI, see the [Quotas and region availability for Azure Container Instances](https://docs.microsoft.com/azure/container-instances/container-instances-quotas) article.
 
-**Using the SDK**
++ **Using the SDK**
 
-```python
-deployment_config = AciWebservice.deploy_configuration(cpu_cores = 1, memory_gb = 1)
-service = Model.deploy(ws, "aciservice", [model], inference_config, deployment_config)
-service.wait_for_deployment(show_output = True)
-print(service.state)
-```
+  ```python
+  deployment_config = AciWebservice.deploy_configuration(cpu_cores = 1, memory_gb = 1)
+  service = Model.deploy(ws, "aciservice", [model], inference_config, deployment_config)
+  service.wait_for_deployment(show_output = True)
+  print(service.state)
+  ```
 
-**Using the CLI**
++ **Using the CLI**
 
-```azurecli-interactive
-az ml model deploy -m sklearn_mnist:1 -n aciservice -ic inferenceconfig.json -dc deploymentconfig.json
-```
+  ```azurecli-interactive
+  az ml model deploy -m sklearn_mnist:1 -n aciservice -ic inferenceconfig.json -dc deploymentconfig.json
+  ```
 
 For more information, see the reference documentation for the [AciWebservice](https://docs.microsoft.com/python/api/azureml-core/azureml.core.webservice.aciwebservice?view=azure-ml-py) and [Webservice](https://docs.microsoft.com/python/api/azureml-core/azureml.core.webservice.webservice?view=azure-ml-py) classes.
 
-### <a id="aks"></a> Deploy to Azure Kubernetes Service (PRODUCTION)
+### <a id="aks"></a>Azure Kubernetes Service (PRODUCTION)
 
 You can use an existing AKS cluster or create a new one using the Azure Machine Learning SDK, CLI, or the Azure portal.
 
 <a id="deploy-aks"></a>
 
-If you already have an AKS cluster attached, you can deploy to it. If you have NOT created or attached an AKS cluster go <a href="#create-attach-aks">here</a>.
+If you already have an AKS cluster attached, you can deploy to it. If you haven't created or attached an AKS cluster, follow the process to <a href="#create-attach-aks">create a new AKS cluster</a>.
 
 
-**Using the SDK**
++ **Using the SDK**
 
-```python
-aks_target = AksCompute(ws,"myaks")
-deployment_config = AksWebservice.deploy_configuration(cpu_cores = 1, memory_gb = 1)
-service = Model.deploy(ws, "aksservice", [model], inference_config, deployment_config, aks_target)
-service.wait_for_deployment(show_output = True)
-print(service.state)
-print(service.get_logs())
-```
+  ```python
+  aks_target = AksCompute(ws,"myaks")
+  deployment_config = AksWebservice.deploy_configuration(cpu_cores = 1, memory_gb = 1)
+  service = Model.deploy(ws, "aksservice", [model], inference_config, deployment_config, aks_target)
+  service.wait_for_deployment(show_output = True)
+  print(service.state)
+  print(service.get_logs())
+  ```
 
-Learn more about AKS deployment and autoscale in the [AksWebservice.deploy_configuration](https://docs.microsoft.com/python/api/azureml-core/azureml.core.webservice.akswebservice) reference.
+  Learn more about AKS deployment and autoscale in the [AksWebservice.deploy_configuration](https://docs.microsoft.com/python/api/azureml-core/azureml.core.webservice.akswebservice) reference.
 
-**Using the CLI**
++ **Using the CLI**
 
-```azurecli-interactive
-az ml model deploy -ct myaks -m mymodel:1 -n aksservice -ic inferenceconfig.json -dc deploymentconfig.json
-```
+  ```azurecli-interactive
+  az ml model deploy -ct myaks -m mymodel:1 -n aksservice -ic inferenceconfig.json -dc deploymentconfig.json
+  ```
 
 #### Create a new AKS cluster<a id="create-attach-aks"></a>
 **Time estimate:** Approximately 5 minutes.