无法将经过训练的模型部署到现有AKS计算目标
我有一个模型是在Azure机器学习服务上的机器学习计算上训练的。已注册的模型已经存在于我的工作区中，我想将其部署到我之前在工作区中提供的一个预先存在的AKS实例中。我能够成功配置和注册容器镜像：
# retrieve cloud representations of the models
rf = Model(workspace=ws, name='pumps_rf')
le = Model(workspace=ws, name='pumps_le')
ohc = Model(workspace=ws, name='pumps_ohc')
print(rf); print(le); print(ohc)
<azureml.core.model.Model object at 0x7f66ab3b1f98>
<azureml.core.model.Model object at 0x7f66ab7e49b0>
<azureml.core.model.Model object at 0x7f66ab85e710>
package_list = [
'category-encoders==1.3.0',
'numpy==1.15.0',
'pandas==0.24.1',
'scikit-learn==0.20.2']
# Conda environment configuration
myenv = CondaDependencies.create(pip_packages=package_list)
conda_yml = 'file:'+os.getcwd()+'/myenv.yml'
with open(conda_yml,"w") as f:
f.write(myenv.serialize_to_string())配置和注册镜像工作：
# Image configuration
image_config = ContainerImage.image_configuration(execution_script='score.py',
runtime='python',
conda_file='myenv.yml',
description='Pumps Random Forest model')
# Register the image from the image configuration
# to Azure Container Registry
image = ContainerImage.create(name = Config.IMAGE_NAME,
models = [rf, le, ohc],
image_config = image_config,
workspace = ws)
Creating image
Running....................
SucceededImage creation operation finished for image pumpsrfimage:2, operation "Succeeded"附加到现有群集也可以：
# Attach the cluster to your workgroup
attach_config = AksCompute.attach_configuration(resource_group = Config.RESOURCE_GROUP,
cluster_name = Config.DEPLOY_COMPUTE)
aks_target = ComputeTarget.attach(workspace=ws,
name=Config.DEPLOY_COMPUTE,
attach_configuration=attach_config)
# Wait for the operation to complete
aks_target.wait_for_completion(True)
SucceededProvisioning operation finished, operation "Succeeded"但是，当我尝试将映像部署到现有集群时，它会失败，并显示WebserviceException。
# Set configuration and service name
aks_config = AksWebservice.deploy_configuration()
# Deploy from image
service = Webservice.deploy_from_image(workspace = ws,
name = 'pumps-aks-service-1' ,
image = image,
deployment_config = aks_config,
deployment_target = aks_target)
# Wait for the deployment to complete
service.wait_for_deployment(show_output = True)
print(service.state)
WebserviceException: Unable to create service with image pumpsrfimage:1 in non "Succeeded" creation state.
---------------------------------------------------------------------------
WebserviceException Traceback (most recent call last)
<command-201219424688503> in <module>()
7 image = image,
8 deployment_config = aks_config,
----> 9 deployment_target = aks_target)
10 # Wait for the deployment to complete
11 service.wait_for_deployment(show_output = True)
/databricks/python/lib/python3.5/site-packages/azureml/core/webservice/webservice.py in deploy_from_image(workspace, name, image, deployment_config, deployment_target)
284 return child._deploy(workspace, name, image, deployment_config, deployment_target)
285
--> 286 return deployment_config._webservice_type._deploy(workspace, name, image, deployment_config, deployment_target)
287
288 @staticmethod
/databricks/python/lib/python3.5/site-packages/azureml/core/webservice/aks.py in _deploy(workspace, name, image, deployment_config, deployment_target)对如何解决这个问题有什么想法吗？我在Databricks笔记本上写代码。此外，我可以使用Azure Portal创建和部署集群，没有问题，所以这似乎是我的代码/Python SDK或Databricks与AMLS的工作方式的问题。
更新:我能够使用Azure Portal将我的镜像部署到AKS，was服务工作正常。这意味着问题存在于Databricks、Azureml Python SDK和Machine Learning Service之间。
更新2:我正在与微软合作来解决这个问题。一旦我们有了解决方案就会报告。
回答 3
Stack Overflow用户
发布于 2019-03-08 04:22:05
在我的初始代码中，当创建图像时，我没有使用：
image.wait_for_creation(show_output=True)因此，我在创建映像之前调用了CreateImage和DeployImage，但出现了错误。不敢相信有这么简单..。
更新的镜像创建片段：
# Register the image from the image configuration
# to Azure Container Registry
image = ContainerImage.create(name = Config.IMAGE_NAME,
models = [rf, le, ohc],
image_config = image_config,
workspace = ws)
image.wait_for_creation(show_output=True)Stack Overflow用户
发布于 2019-02-21 23:56:25
根据个人经验，我会说你看到的错误消息可能表明图像中的脚本有一些错误。这样的错误不一定会阻止镜像的成功创建，但它可能会阻止镜像在服务中使用。但是，如果您已经能够成功地在其他服务中部署映像，那么您应该能够排除此选项。
您可以关注this guide，了解有关如何在本地调试Docker镜像的更多信息，以及查找日志和其他有用信息。
Stack Overflow用户
发布于 2019-03-04 21:54:29
同意Arvid的回答。你能成功地运行它吗？您也可以尝试将其部署到ACI，但如果问题出在score.py中，您也会遇到相同的问题，但它很快就会尝试。此外，如果您想调试部署，也会有点痛苦，但您可以公开本地docker部署上的TCP5678端口，并使用VSCode和PTVSD连接到该端口并逐步进行调试。
https://stackoverflow.com/questions/54796762
复制相似问题
腾讯云开发者
