为什么我收到此错误："Received bad response from Model Management Service:nResponse Code: 403" 在尝试 de 时

Question

这是我的代码，我试图在Azure AML上部署我的模型:

aciconfig = AciWebservice.deploy_configuration(
cpu_cores=1,
memory_gb=1,
tags={"data":"nlp classifier"},
description='nlp cLASSIFICATION  MODEL'
)
inference_config = InferenceConfig(entry_script="scoringscript.py", environment=myenv)
service = Model.deploy(workspace=ws,
name='nlpse',
models=[model],
inference_config=inference_config,
deployment_config=aciconfig, 
overwrite = True)
service.wait_for_deployment(show_output=True)
url = service.scoring_uri
print(url)

然而，我得到这个错误:

WebserviceException: WebserviceException:
Message: Received bad response from Model Management Service:
Response Code: 403
Headers: {'Server': 'nginx/1.22.1', 'Date': 'Fri, 25 Nov 2022 19:33:11 GMT', 'Content-Type': 'application/json', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Vary': 'Accept-Encoding', 'x-ms-client-request-id': 'dff1b808-aa1c-4b6d-9bf4-0b43325131b2', 'x-ms-client-session-id': '07e975c4-02fa-47ce-8ee6-cd2f808d53c1', 'api-supported-versions': '1.0, 2018-03-01-preview, 2018-11-19', 'Strict-Transport-Security': 'max-age=15724800; includeSubDomains; preload', 'X-Content-Type-Options': 'nosniff', 'x-aml-cluster': 'vienna-centralus-01', 'x-request-time': '0.630', 'Content-Encoding': 'gzip'}
Content: b'{"code":"Forbidden","statusCode":403,"message":"Forbidden","details":[{"code":"UserError","message":"KeyVaultErrorException encountered. Operation returned an invalid status code 'Forbidden'"}],"correlation":{"RequestId":"dff1b808-aa1c-4b6d-9bf4-0b43325131b2"}}'
InnerException None
ErrorResponse 
{
"error": {
"message": "Received bad response from Model Management Service:nResponse Code: 403nHeaders: {'Server': 'nginx/1.22.1', 'Date': 'Fri, 25 Nov 2022 19:33:11 GMT', 'Content-Type': 'application/json', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Vary': 'Accept-Encoding', 'x-ms-client-request-id': 'dff1b808-aa1c-4b6d-9bf4-0b43325131b2', 'x-ms-client-session-id': '07e975c4-02fa-47ce-8ee6-cd2f808d53c1', 'api-supported-versions': '1.0, 2018-03-01-preview, 2018-11-19', 'Strict-Transport-Security': 'max-age=15724800; includeSubDomains; preload', 'X-Content-Type-Options': 'nosniff', 'x-aml-cluster': 'vienna-centralus-01', 'x-request-time': '0.630', 'Content-Encoding': 'gzip'}nContent: b'{"code":"Forbidden","statusCode":403,"message":"Forbidden","details":[{"code":"UserError","message":"KeyVaultErrorException encountered. Operation returned an invalid status code \'Forbidden\'"}],"correlation":{"RequestId":"dff1b808-aa1c-4b6d-9bf4-0b43325131b2"}}'"
}
}

如何解决?

Answer 1

• 我试图重现这个问题，它为我工作。

aciconfig = AciWebservice.deploy_configuration(
cpu_cores=1,
memory_gb=1,
tags={"data":"nlp classifier"},
description='nlp  cLASSIFICATION MODEL'
)
inference_config = InferenceConfig(entry_script="scoringscript.py", environment=myenv)
service = Model.deploy(workspace=ws,
name='nlpse',
models=[model],
inference_config=inference_config,
deployment_config=aciconfig,
overwrite = True)
service.wait_for_deployment(show_output=True)
url = service.scoring_uri
print(url)

• 从上面的代码块中，service.wait_for_deployment(show_output=True)在代码块开始执行时被初始调用。它让管道等待很长时间，因此它在TTL之后断开连接。

• service.wait_for_deployment(show_output=True)->在获得配置和服务详细信息之后，我们需要执行服务等待方法。这将解决连接错误。