Watson机器学习部署需要太多时间

时间:2018-11-29 09:35:54

标签: ibm-cloud ibm-watson ibm-cloud-plugin

我使用Watson Machine Learning Service训练了一个模型。培训过程已经完成,所以我运行了以下命令行进行部署:

bx ml store training-runs model-XXXXXXX

我得到带有模型ID的输出

Starting to store the training-run 'model-XXXXXX' ...
OK
Model store successful. Model-ID is '93sdsdsf05-3ea4-4d9e-a751-5bcfbsdsd3391'.

然后我使用以下内容进行部署:

bx ml deploy 93sdsdsf05-3ea4-4d9e-a751-5bcfbsdsd3391 "my-test-model"

问题是我收到无尽的信息:

Checking if content upload is complete ...
Checking if content upload is complete ...
Checking if content upload is complete ...
Checking if content upload is complete ...
Checking if content upload is complete ...

当我在COS结果存储区中签入时,模型大小约为25MB,因此部署时间不会太长。我在这里想念什么吗?

1 个答案:

答案 0 :(得分:0)

使用<a4j:commandButton type="button" .../> 部署相同的模型:

Python Client API

这很快告诉我部署存在错误。奇怪的是,使用from watson_machine_learning_client import WatsonMachineLearningAPIClient client = WatsonMachineLearningAPIClient(wml_credentials) deployment_details = client.deployments.create( model_id, "model_name") 进行部署时,错误不会弹出。