def prepare_remote_compute(ws):
compute_name = os.environ.get("AML_COMPUTE_CLUSTER_NAME", "cpucluster")
compute_min_nodes = os.environ.get("AML_COMPUTE_CLUSTER_MIN_NODES", 1)
compute_max_nodes = os.environ.get("AML_COMPUTE_CLUSTER_MAX_NODES", 4)
# This example uses CPU VM. For using GPU VM, set SKU to STANDARD_NC6
vm_size = os.environ.get("AML_COMPUTE_CLUSTER_SKU", "STANDARD_D2_V2")
if compute_name in ws.compute_targets:
compute_target = ws.compute_targets[compute_name]
if compute_target and type(compute_target) is AmlCompute:
print('found compute target. Using it. ' + compute_name)
else:
print('creating a new compute target...')
provisioning_config = AmlCompute.provisioning_configuration(
vm_size=vm_size,
min_nodes=compute_min_nodes,
max_nodes=compute_max_nodes)
# create the cluster
compute_target = ComputeTarget.create(ws, compute_name,
provisioning_config)
# can poll for a minimum number of nodes and for a specific timeout.
# if no min node count is provided it will use the scale settings for the cluster
compute_target.wait_for_completion(show_output=True,
min_node_count=None,
timeout_in_minutes=20)
# For a more detailed view of current AmlCompute status, use get_status()
print(compute_target.get_status().serialize())
return compute_target
def main(name, vm_size, nodes):
ws = Workspace.from_config()
try:
compute_cluster = ComputeTarget(ws, name)
except:
compute_config = AmlCompute.provisioning_configuration(vm_size=vm_size,
min_nodes=1,
max_nodes=nodes)
compute_cluster = ComputeTarget.create(ws, name, compute_config)
compute_cluster.wait_for_completion(show_output=True)
def prepare_remote_compute(ws,
compute_name,
compute_min_nodes=0,
compute_max_nodes=4,
compute_vm_size='STANDARD_D2_V2'):
"""
:param ws: azureml Workspace instance
:param compute_name: String with name for compute target
:param compute_min_nodes: minimum number of nodes
:param compute_max_nodes: maximum number of nodes
:param compute_vm_size: vm size for compute target
:return:
"""
if compute_name in ws.compute_targets:
compute_target = ws.compute_targets[compute_name]
if compute_target and type(compute_target) is AmlCompute:
print('Found compute target: ' + compute_name + ' of size: ' +
compute_target.vm_size + '. Using it. ')
print(
'For a different size create a new target with different name!'
)
# TODO: Handle case if compute_name exists, but is not active!
else:
print('creating a new compute target...')
provisioning_config = AmlCompute.provisioning_configuration(
vm_size=compute_vm_size,
min_nodes=compute_min_nodes,
max_nodes=compute_max_nodes)
# create the cluster
compute_target = ComputeTarget.create(ws, compute_name,
provisioning_config)
# can poll for a minimum number of nodes and for a specific timeout.
# if no min node count is provided it will use the scale settings for the cluster
compute_target.wait_for_completion(show_output=True,
min_node_count=None,
timeout_in_minutes=20)
# For a more detailed view of current AmlCompute status, use get_status()
print(compute_target.get_status().serialize())
return compute_target
variables[d['name']] = d['value']
# Check if compute cluster exists. If not, create one.
try:
compute_target = ComputeTarget(aml_workspace,
variables["AML_COMPUTE_CLUSTER_CPU_SKU"])
print('Found existing cluster, use it.')
except ComputeTargetException:
compute_config = AmlCompute.provisioning_configuration(
vm_size=variables['AML_COMPUTE_CLUSTER_SIZE'],
vm_priority=variables['AML_CLUSTER_PRIORITY'],
min_nodes=variables['AML_CLUSTER_MIN_NODES'],
max_nodes=variables['AML_CLUSTER_MAX_NODES'],
idle_seconds_before_scaledown="300")
cpu_cluster = ComputeTarget.create(
aml_workspace, variables["AML_COMPUTE_CLUSTER_CPU_SKU"],
compute_config)
#create environment from conda_dependencies.yml for runconfig
environment = Environment(name="myenv")
conda_dep = CondaDependencies(
conda_dependencies_file_path="conda_dependencies.yml")
environment.python.conda_dependencies = conda_dep
run_config = RunConfiguration()
run_config.environment = environment
#Dataset creation
dataset_name = variables["DATASET_NAME"]
#Check to see if dataset exists
if (dataset_name not in aml_workspace.datasets):
'Azure region: ' + workspace.location,
'Subscription id: ' + workspace.subscription_id,
'Resource group: ' + workspace.resource_group,
sep='\n')
# Getting an Azure ML Compute Target
try:
compute_target = ComputeTarget(workspace=workspace, name=cluster_name)
print('Found existing compute target')
except ComputeTargetException:
print('Creating a new compute target...')
compute_config = AmlCompute.provisioning_configuration(
vm_size='STANDARD_D3_V2', max_nodes=1)
# create the cluster
compute_target = ComputeTarget.create(workspace, cluster_name,
compute_config)
# can poll for a minimum number of nodes and for a specific timeout.
# if no min node count is provided it uses the scale settings for the cluster
compute_target.wait_for_completion(show_output=True,
min_node_count=None,
timeout_in_minutes=20)
# store the connection string in AML workspace Key Vault
# (secret name is 'debugrelay-' + MD5(azrelay_connection_string) )
#hybrid_connection_string_secret =\
# f"debugrelay-{hashlib.md5(azrelay_connection_string.encode('utf-8')).hexdigest()}"
#workspace.get_default_keyvault().set_secret(hybrid_connection_string_secret, azrelay_connection_string)
# Configuring a PythonScriptStep with a RunConfiguration
# that includes debugpy and azure-debug-relay