def load_data(dataset, input_name):
data = Data(
data_location=DataLocation(dataset=RunDataset(dataset_id=dataset.id)),
create_output_directories=False,
mechanism='mount',
environment_variable_name=input_name,
overwrite=True)
return data
compute_name = 'cpu-cluster'
# Define the script run config
src = ScriptRunConfig(
source_directory='scripts',
script='train.py',
arguments=[
'--data-folder',
'DatasetConsumptionConfig:{}'.format(input_name)
])
# Define the data section of the runconfig
src.run_config.data = {
input_name: Data(
data_location=DataLocation(
dataset=RunDataset(dataset_id=dataset.id)),
create_output_directories=False,
mechanism='mount',
environment_variable_name=input_name,
overwrite=False
)
}
# Set other parameters for the run
src.run_config.framework = 'python'
src.run_config.environment = conda_env
src.run_config.target = compute_name
src.run_config.node_count = 4
# Save the run configuration as a .azureml/mnist.runconfig
get_run_config_from_script_run(src).save(name='mnist.runconfig')
# Define the environment variable/where data will be mounted
input_name = 'mnist'
# Define the name of the compute target for training
compute_name = 'cpu-cluster'
# Define the script run config
src = ScriptRunConfig(source_directory='scripts',
script='train.py',
arguments=[
'--data-folder',
'DatasetConsumptionConfig:{}'.format(input_name)
])
# Define the data section of the runconfig
src.run_config.data = {
input_name:
Data(data_location=DataLocation(dataset=RunDataset(dataset_id=dataset.id)),
create_output_directories=False,
mechanism='mount',
environment_variable_name=input_name,
overwrite=False)
}
# Set other parameters for the run
src.run_config.framework = 'python'
src.run_config.environment = conda_env
src.run_config.target = compute_name
src.run_config.node_count = 4
# Save the run configuration as a .azureml/mnist.runconfig
get_run_config_from_script_run(src).save(name='mnist.runconfig')