繁体   English   中英

Watson机器学习部署需要太多时间

[英]Watson machine learning deployment takes too much time

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

bx ml store training-runs model-XXXXXXX

我得到带有型号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消息说:

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结果存储区时,模型大小为〜25MB,因此部署时间不应该太长。 我在这里想念什么吗?

使用Python Client API部署相同的模型:

from watson_machine_learning_client import WatsonMachineLearningAPIClient

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

这很快就告诉我部署存在错误。 奇怪的是,使用command line interface (CLI)部署时,错误不会弹出。

暂无
暂无

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM