我用沃森机器学习服务训练了一个模型。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,我使用以下方法部署它:
bx ml deploy 93sdsdsf05-3ea4-4d9e-a751-5bcfbsdsd3391 "my-test-model"问题是我收到了一条无穷无尽的信息:
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 ...当我签入COS结果桶时,模型大小约为25 to,因此应该不会太长时间部署。我是不是漏掉了什么?
发布于 2019-01-22 16:02:34
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")这很快就向我展示了部署中的一个错误。奇怪的是,使用command line interface (CLI)部署时不会出现错误。
https://stackoverflow.com/questions/53535848
复制相似问题