def create_and_submit_experiment(
azure_config: AzureConfig,
source_config: SourceConfig,
model_config_overrides: str,
azure_dataset_id: str) -> Run:
"""
Creates an AzureML experiment in the workspace and submits it for execution.
:param azure_config: azure related configurations to setup valid workspace
:param source_config: The information about which code should be submitted, and which arguments should be used.
:param model_config_overrides: A string that describes which model parameters were overwritten by commandline
arguments in the present run. This is only used for diagnostic purposes (it is set as a Tag on the run).
:param azure_dataset_id: The name of the dataset in blob storage to be used for this run.
:returns: Run object for the submitted AzureML run
"""
workspace = azure_config.get_workspace()
experiment_name = create_experiment_name(azure_config)
exp = Experiment(workspace=workspace, name=azure_util.to_azure_friendly_string(experiment_name))
script_run_config = create_run_config(azure_config, source_config, azure_dataset_id)
# submit a training/testing run associated with the experiment
run: Run = exp.submit(script_run_config)
# set metadata for the run
set_run_tags(run, azure_config, model_config_overrides)
print("\n==============================================================================")
print(f"Successfully queued new run {run.id} in experiment: {exp.name}")
if azure_config.run_recovery_id:
print(f"\nRecovered from: {azure_config.run_recovery_id}")
recovery_id = azure_util.create_run_recovery_id(run)
recovery_file = Path(RUN_RECOVERY_FILE)
if recovery_file.exists():
recovery_file.unlink()
recovery_file.write_text(recovery_id)
print("Experiment URL: {}".format(exp.get_portal_url()))
print("Run URL: {}".format(run.get_portal_url()))
print("If this run fails, re-start runner.py and supply these additional arguments: "
f"--run_recovery_id={recovery_id}")
print(f"The run recovery ID has been written to this file: {recovery_file}")
print("==============================================================================")
if azure_config.tensorboard and azure_config.azureml:
print("Starting TensorBoard now because you specified --tensorboard")
monitor(monitor_config=AMLTensorBoardMonitorConfig(run_ids=[run.id]), azure_config=azure_config)
else:
print(f"To monitor this run locally using TensorBoard, run the script: "
f"InnerEye/Azure/tensorboard_monitor.py --run_ids={run.id}")
print("==============================================================================")
return run
def after_submission_hook(azure_run: Run) -> None:
"""
A function that will be called right after job submission.
"""
# Set the default display name to what was provided as the "tag". This will affect single runs
# and Hyperdrive parent runs
if self.azure_config.tag:
azure_run.display_name = self.azure_config.tag
# Add an extra tag that depends on the run that was actually submitted. This is used for later filtering
# run in cross validation analysis
recovery_id = create_run_recovery_id(azure_run)
azure_run.tag(RUN_RECOVERY_ID_KEY_NAME, recovery_id)
print(
"If this run fails, re-start runner.py and supply these additional arguments: "
f"--run_recovery_id={recovery_id}")
if self.azure_config.tensorboard:
print(
"Starting TensorBoard now because you specified --tensorboard"
)
monitor(monitor_config=AMLTensorBoardMonitorConfig(
run_ids=[azure_run.id]),
azure_config=self.azure_config)
else:
print(
f"To monitor this run locally using TensorBoard, run the script: "
f"InnerEye/Azure/tensorboard_monitor.py --run_ids={azure_run.id}"
)
if self.azure_config.wait_for_completion:
# We want the job output to be visible on the console. Do not exit yet if the job fails, because we
# may need to download the pytest result file.
azure_run.wait_for_completion(show_output=True,
raise_on_error=False)
if self.azure_config.pytest_mark:
# The AzureML job can optionally run pytest. Attempt to download it to the current directory.
# A build step will pick up that file and publish it to Azure DevOps.
# If pytest_mark is set, this file must exist.
logging.info("Downloading pytest result file.")
download_pytest_result(azure_run)
if azure_run.status == RunStatus.FAILED:
raise ValueError(
f"The AzureML run failed. Please check this URL for details: "
f"{azure_run.get_portal_url()}")
def create_and_submit_experiment(azure_config: AzureConfig,
script_run_config: ScriptRunConfig,
commandline_args: str) -> Run:
"""
Creates an AzureML experiment in the workspace and submits it for execution.
:param azure_config: azure related configurations to setup a valid workspace.
:param script_run_config: The configuration for the script that should be run inside of AzureML.
:param commandline_args: A string with all commandline arguments that were provided to the runner. These are only
used to set a tag on the submitted AzureML run.
:returns: Run object for the submitted AzureML run
"""
workspace = azure_config.get_workspace()
experiment_name = create_experiment_name(azure_config)
exp = Experiment(workspace=workspace,
name=azure_util.to_azure_friendly_string(experiment_name))
# submit a training/testing run associated with the experiment
run: Run = exp.submit(script_run_config)
if is_offline_run_context(run):
# This codepath will only be executed in unit tests, when exp.submit is mocked.
return run
# Set metadata for the run.
set_run_tags(run, azure_config, commandline_args=commandline_args)
print(
"\n=============================================================================="
)
print(f"Successfully queued new run {run.id} in experiment: {exp.name}")
if azure_config.run_recovery_id:
print(f"\nRecovered from: {azure_config.run_recovery_id}")
recovery_id = azure_util.create_run_recovery_id(run)
recovery_file = Path(RUN_RECOVERY_FILE)
if recovery_file.exists():
recovery_file.unlink()
recovery_file.write_text(recovery_id)
print("Experiment URL: {}".format(exp.get_portal_url()))
print("Run URL: {}".format(run.get_portal_url()))
print(
"If this run fails, re-start runner.py and supply these additional arguments: "
f"--run_recovery_id={recovery_id}")
print(
f"The run recovery ID has been written to this file: {recovery_file}")
print(
"=============================================================================="
)
if azure_config.tensorboard and azure_config.azureml:
print("Starting TensorBoard now because you specified --tensorboard")
monitor(monitor_config=AMLTensorBoardMonitorConfig(run_ids=[run.id]),
azure_config=azure_config)
else:
print(
f"To monitor this run locally using TensorBoard, run the script: "
f"InnerEye/Azure/tensorboard_monitor.py --run_ids={run.id}")
print(
"=============================================================================="
)
return run
