我
registered a
model
现在想将其部署为ACI web服务,如中所示
the guide
.
为此,我定义
from azureml.core.webservice import Webservice, AciWebservice
from azureml.core.image import ContainerImage
aciconfig = AciWebservice.deploy_configuration(cpu_cores=4,
memory_gb=32,
tags={"data": "text", "method" : "NB"},
description='Predict something')
image_config = ContainerImage.image_configuration(execution_script="score.py",
docker_file="Dockerfile",
runtime="python",
conda_file="myenv.yml")
并用
image = ContainerImage.create(name = "scorer-image",
models = [model],
image_config = image_config,
workspace = ws
)
为图像创建图像的操作已完成
记分员-图片:5,操作“成功”
另外,通过在带有
sudo docker run -p 8002:5001 myscorer0588419434.azurecr.io/scorer-image:5
允许我对成功运行(本地)查询
http://localhost:8002/score
.
但是,部署
service_name = 'scorer-svc'
service = Webservice.deploy_from_image(deployment_config = aciconfig,
image = image,
name = service_name,
workspace = ws)
失败于
创建服务
跑步。
服务创建轮询已达到终端状态,当前服务状态:正在转换
服务创建轮询达到终端状态,收到意外响应。过渡
aciconfig
更慷慨
memory_gb
,但无济于事:部署停留在
状态(如下图所示,如果在Azure门户上监视):
service.get_logs()
给了我
WebserviceException:收到来自模型管理的错误响应
什么可能是罪魁祸首?