0

这个例子

library(azuremlsdk)
library(jsonlite)

ws <- load_workspace_from_config()

# Register the model
model <- register_model(ws, model_path = "model.rds", model_name = "model.rds")

# Create environment
r_env <- r_environment(name = "r_env")

# Create inference config
inference_config <- inference_config(
  entry_script = "score.R",
  source_directory = ".",
  environment = r_env)

# Create ACI deployment config
deployment_config <- aci_webservice_deployment_config(cpu_cores = 1,
                                                      memory_gb = 1)

# Deploy the web service
service_name <- paste0('aciwebservice-', sample(1:100, 1, replace=TRUE))
service <- deploy_model(ws, 
                        service_name, 
                        list(model), 
                        inference_config, 
                        deployment_config)
wait_for_deployment(service, show_output = TRUE)

难道是 score.R 必须上传到 Azure 环境,而不是本地的,因为它在开发机器上?我目前的想法是,那个 source_directory 。指的是本地系统(即在开发机器上)?

4

1 回答 1

1

source_directory指的是本地系统(即在开发机器上)?

正确的。并且entry_script应该是在source_directory. 如果entry_script引用其他文件,它们也应该在source_directory. SDK 将处理您的源目录的快照并将其上传到远程计算。

因此,建议您将要在远程计算上运行的代码与项目的其余部分隔离开,如下所示。中source_directory=./scoring的什么地方deploy-to-aci.R

dir/
    deploy-to-aci.R
    scoring/
        score.R
    sensitive_data.csv
于 2021-05-17T14:13:53.903 回答