Run.get_context() 给出相同的 运行 id

Run.get_context() gives the same run id

我正在通过脚本文件提交培训。以下是 train.py 脚本的内容。 Azure ML 将所有这些视为一个 运行(而不是下面编码的每个 alpha 值 运行),因为 Run.get_context() 返回相同的 运行 id。

train.py

from azureml.opendatasets import Diabetes
from azureml.core import Run

from sklearn.model_selection import train_test_split
from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error
from sklearn.externals import joblib

import math
import os
import logging

# Load dataset
dataset = Diabetes.get_tabular_dataset()
print(dataset.take(1))

df = dataset.to_pandas_dataframe()
df.describe()

# Split X (independent variables) & Y (target variable)
x_df = df.dropna()      # Remove rows that have missing values
y_df = x_df.pop("Y")    # Y is the label/target variable

x_train, x_test, y_train, y_test = train_test_split(x_df, y_df, test_size=0.2, random_state=66)
print('Original dataset size:', df.size)
print("Size after dropping 'na':", x_df.size)
print("Training split size: ", x_train.size)
print("Test split size: ", x_test.size)

# Training
alphas = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0] # Define hyperparameters

# Create and log interactive runs

output_dir = os.path.join(os.getcwd(), 'outputs')

for hyperparam_alpha in alphas:
    # Get the experiment run context
    run = Run.get_context()
    print("Started run: ", run.id)
    run.log("train_split_size", x_train.size)
    run.log("test_split_size", x_train.size)
    run.log("alpha_value", hyperparam_alpha)

    # Train
    print("Train ...")
    model = Ridge(hyperparam_alpha)
    model.fit(X = x_train, y = y_train)
    
    # Predict
    print("Predict ...")
    y_pred = model.predict(X = x_test)

    # Calculate & log error
    rmse = math.sqrt(mean_squared_error(y_true = y_test, y_pred = y_pred))
    run.log("rmse", rmse)
    print("rmse", rmse)

    # Serialize the model to local directory
    if not os.path.isdir(output_dir):
        os.makedirs(output_dir, exist_ok=True) 

    print("Save model ...")
    model_name = "model_alpha_" + str(hyperparam_alpha) + ".pkl" # Pickle file
    file_path = os.path.join(output_dir, model_name)
    joblib.dump(value = model, filename = file_path)

    # Upload the model
    run.upload_file(name = model_name, path_or_stream = file_path)

    # Complete the run
    run.complete()

实验视图

创作代码(即控制平面)

import os
from azureml.core import Workspace, Experiment, RunConfiguration, ScriptRunConfig, VERSION, Run

ws = Workspace.from_config()
exp = Experiment(workspace = ws, name = "diabetes-local-script-file")

# Create new run config obj
run_local_config = RunConfiguration()

# This means that when we run locally, all dependencies are already provided.
run_local_config.environment.python.user_managed_dependencies = True

# Create new script config
script_run_cfg = ScriptRunConfig(
    source_directory =  os.path.join(os.getcwd(), 'code'),
    script = 'train.py',
    run_config = run_local_config) 

run = exp.submit(script_run_cfg)
run.wait_for_completion(show_output=True)

简答

选项 1:在 运行

内创建 child 运行 秒

run = Run.get_context() 将您当前所在 运行 的 运行 object 分配给 run。因此,在超参数搜索的每次迭代中,您都登录到相同的 运行。要解决这个问题,您需要为每个超参数值创建 child(或子)运行。您可以使用 run.child_run() 执行此操作。以下是实现此目的的模板。

run = Run.get_context()

for hyperparam_alpha in alphas:
    # Get the experiment run context
    run_child = run.child_run()
    print("Started run: ", run_child.id)
    run_child.log("train_split_size", x_train.size)

diabetes-local-script-file 实验页面上,您可以看到 运行 9 是 parent 运行 和 运行 的 10-19 是 child 运行,如果您单击“包含 child 运行”页面。 运行 9 详细信息页面上还有一个“Child 运行s”选项卡。

长答案

我强烈建议将超参数搜索从数据平面(即 train.py)抽象到控制平面(即“编写代码”)。随着训练时间的增加,这变得特别有价值,您可以任意并行化,也可以使用 Azure ML Hyperdrive.

更智能地选择超参数

选项 2 从控制平面创建 运行s

从代码中删除循环,添加如下代码 (full data and control here)

import argparse
from pprint import pprint

parser = argparse.ArgumentParser()
parser.add_argument('--alpha', type=float, default=0.5)
args = parser.parse_args()
print("all args:")
pprint(vars(args))

# use the variable like this
model = Ridge(args.alpha)

下面是如何使用脚本参数提交单个 运行。要提交多个 运行,只需在控制平面中使用循环即可。

alphas = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0] # Define hyperparameters

list_rcs = [ScriptRunConfig(
    source_directory =  os.path.join(os.getcwd(), 'code'),
    script = 'train.py',
    arguments=['--alpha',a],
    run_config = run_local_config) for a in alphas]

list_runs = [exp.submit(rc) for rc in list_rcs]

选项 3 Hyperdrive(恕我直言,推荐方法)

通过这种方式,您可以将超参数源外包给 Hyperdrive。 UI 还将准确报告您想要的结果,并且通过 API 您可以轻松下载最佳模型。请注意,您不能再在本地使用它,必须使用 AMLCompute,但对我来说这是值得的 trade-off.This is a great overview. Excerpt below (full code here)

param_sampling = GridParameterSampling( {
        "alpha": choice(0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0)
    }
)

estimator = Estimator(
    source_directory =  os.path.join(os.getcwd(), 'code'),
    entry_script = 'train.py',
    compute_target=cpu_cluster,
    environment_definition=Environment.get(workspace=ws, name="AzureML-Tutorial")
)

hyperdrive_run_config = HyperDriveConfig(estimator=estimator,
                          hyperparameter_sampling=param_sampling, 
                          policy=None,
                          primary_metric_name="rmse", 
                          primary_metric_goal=PrimaryMetricGoal.MAXIMIZE,
                          max_total_runs=10,
                          max_concurrent_runs=4)

run = exp.submit(hyperdrive_run_config)
run.wait_for_completion(show_output=True)