0

我使用 watson 机器学习服务训练了一个模型。训练过程已经完成,所以我运行了这些命令行来部署它:

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来部署它:

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

问题是我收到一条没完没了的消息:

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 ...

当我签入 COS 结果存储桶时,模型大小约为 25MB,因此部署时间不应该那么长。我在这里错过了什么吗?

4

1 回答 1

0

使用以下方法部署相同的模型Python Client API

from watson_machine_learning_client import WatsonMachineLearningAPIClient

client = WatsonMachineLearningAPIClient(wml_credentials)
deployment_details = client.deployments.create( model_id, "model_name")

这很快向我表明部署存在错误。奇怪的是,使用command line interface (CLI).

于 2019-01-22T16:02:34.897 回答