def hyperparameter_tuning(ws,experiment):
# Create and submit a Hyperdrive job
cluster = ws.compute_targets[AML.compute_name]
script_params={
'--datastore-dir': ws.get_default_datastore().as_mount(),
}
tf_estimator = TensorFlow(source_directory='scripts',
compute_target=cluster,
entry_script='train.py',
script_params=script_params,
use_gpu=True)
ps = RandomParameterSampling(
{
'--learning-rate': loguniform(-15, -3)
}
)
early_termination_policy = BanditPolicy(slack_factor = 0.15, evaluation_interval=2)
hyperdrive_run_config = HyperDriveRunConfig(estimator = tf_estimator,
hyperparameter_sampling = ps,
policy = early_termination_policy,
primary_metric_name = "validation_accuracy",
primary_metric_goal = PrimaryMetricGoal.MAXIMIZE,
max_total_runs = 20,
max_concurrent_runs = 4)
hd_run = experiment.submit(hyperdrive_run_config)
RunDetails(Run(experiment, hd_run.id)).show()
return hd_run
def get_parameter_distribution(distribution, **kwargs):
if "choice" in distribution.lower():
parameter_distr = choice(
kwargs.get("options", [])
)
elif "randint" in distribution.lower():
parameter_distr = randint(
upper=kwargs.get("upper", None)
)
elif "uniform" in distribution.lower():
parameter_distr = uniform(
min_value=kwargs.get("min_value", None),
max_value=kwargs.get("max_value", None)
)
elif "quniform" in distribution.lower():
parameter_distr = quniform(
min_value=kwargs.get("min_value", None),
max_value=kwargs.get("max_value", None),
q=kwargs.get("q", None)
)
elif "loguniform" in distribution.lower():
parameter_distr = loguniform(
min_value=kwargs.get("min_value", None),
max_value=kwargs.get("max_value", None),
)
elif "qloguniform" in distribution.lower():
parameter_distr = qloguniform(
min_value=kwargs.get("min_value", None),
max_value=kwargs.get("max_value", None),
q=kwargs.get("q", None)
)
elif "normal" in distribution.lower():
parameter_distr = normal(
mu=kwargs.get("mu", None),
sigma=kwargs.get("sigma", None)
)
elif "qnormal" in distribution.lower():
parameter_distr = qnormal(
mu=kwargs.get("mu", None),
sigma=kwargs.get("sigma", None),
q=kwargs.get("q", None)
)
elif "lognormal" in distribution.lower():
parameter_distr = lognormal(
mu=kwargs.get("mu", None),
sigma=kwargs.get("sigma", None)
)
elif "qlognormal" in distribution.lower():
parameter_distr = qlognormal(
mu=kwargs.get("mu", None),
sigma=kwargs.get("sigma", None),
q=kwargs.get("q", None)
)
else:
parameter_distr = None
raise RunConfigurationException(f"Parameter distribution for parameter not defined in settings. Please choose between \'choice\', \'randint\', \'uniform\', \'quniform\', \'loguniform\', \'qloguniform\', \'normal\', \'qnormal\', \'lognormal\' and \'qlognormal\'")
return parameter_distr
def main(epochs, iterations, compute_target, concurrent_runs):
cli_auth = AzureCliAuthentication()
experiment = Experiment.from_directory(".", auth=cli_auth)
ws = experiment.workspace
cluster = ws.compute_targets[compute_target]
food_data = ws.datastores['food_images']
script_arguments = {"--data-dir": food_data.as_mount(), "--epochs": epochs}
tf_est = TensorFlow(source_directory=".",
entry_script='code/train/train.py',
script_params=script_arguments,
compute_target=cluster,
conda_packages=['pillow', 'pandas'],
pip_packages=['click', 'seaborn'],
use_docker=True,
use_gpu=True,
framework_version='1.13')
# Run on subset of food categories
tf_est.run_config.arguments.extend(
['apple_pie', 'baby_back_ribs', 'baklava', 'beef_carpaccio'])
param_sampler = RandomParameterSampling({
'--minibatch-size':
choice(16, 32, 64),
'--learning-rate':
loguniform(-9, -6),
'--optimizer':
choice('rmsprop', 'adagrad', 'adam')
})
# Create Early Termination Policy
etpolicy = BanditPolicy(evaluation_interval=2, slack_factor=0.1)
# Create HyperDrive Run Configuration
hyper_drive_config = HyperDriveConfig(
estimator=tf_est,
hyperparameter_sampling=param_sampler,
policy=etpolicy,
primary_metric_name='acc',
primary_metric_goal=PrimaryMetricGoal.MAXIMIZE,
max_total_runs=iterations,
max_concurrent_runs=concurrent_runs)
# Submit the Hyperdrive Run
print("Submitting Hyperdrive Run")
hd_run = experiment.submit(hyper_drive_config)
hd_run.wait_for_completion(raise_on_error=True, show_output=True)
print("Finishing Run")
best_run = hd_run.get_best_run_by_primary_metric()
print(f'##vso[task.setvariable variable=run_id]{best_run.id}')
def get_parameter_distribution(parameter_name, parameter_setting):
if "choice" in parameter_setting["distribution"]:
parameter_distr = choice(parameter_setting["parameters"]["options"])
elif "randint" in parameter_setting["distribution"]:
parameter_distr = randint(
upper=parameter_setting["parameters"]["upper"])
elif "uniform" in parameter_setting["distribution"]:
parameter_distr = uniform(
min_value=parameter_setting["parameters"]["min_value"],
max_value=parameter_setting["parameters"]["max_value"])
elif "quniform" in parameter_setting["distribution"]:
parameter_distr = quniform(
min_value=parameter_setting["parameters"]["min_value"],
max_value=parameter_setting["parameters"]["max_value"],
q=parameter_setting["parameters"]["q"])
elif "loguniform" in parameter_setting["distribution"]:
parameter_distr = loguniform(
min_value=parameter_setting["parameters"]["min_value"],
max_value=parameter_setting["parameters"]["max_value"])
elif "qloguniform" in parameter_setting["distribution"]:
parameter_distr = qloguniform(
min_value=parameter_setting["parameters"]["min_value"],
max_value=parameter_setting["parameters"]["max_value"],
q=parameter_setting["parameters"]["q"])
elif "normal" in parameter_setting["distribution"]:
parameter_distr = normal(
mu=parameter_setting["parameters"]["mu"],
sigma=parameter_setting["parameters"]["sigma"])
elif "qnormal" in parameter_setting["distribution"]:
parameter_distr = qnormal(
mu=parameter_setting["parameters"]["mu"],
sigma=parameter_setting["parameters"]["sigma"],
q=parameter_setting["parameters"]["q"])
elif "lognormal" in parameter_setting["distribution"]:
parameter_distr = lognormal(
mu=parameter_setting["parameters"]["mu"],
sigma=parameter_setting["parameters"]["sigma"])
elif "qlognormal" in parameter_setting["distribution"]:
parameter_distr = qlognormal(
mu=parameter_setting["parameters"]["mu"],
sigma=parameter_setting["parameters"]["sigma"],
q=parameter_setting["parameters"]["q"])
else:
parameter_distr = None
raise RunConfigurationException(
"Parameter distribution for parameter {} not defined in settings. Please choose between \'choice\', \'randint\', \'uniform\', \'quniform\', \'loguniform\', \'qloguniform\', \'normal\', \'qnormal\', \'lognormal\' and \'qlognormal\'"
.format(parameter_name))
return parameter_distr
5,
"--weight_decay",
0.01, # will be overridden by HyperDrive
"--disable_tqdm",
True,
],
compute_target=target,
environment=env,
)
# set up hyperdrive search space
convert_base = lambda x: float(np.log(x))
search_space = {
"--learning_rate":
hyperdrive.loguniform(
convert_base(1e-6),
convert_base(5e-2)), # NB. loguniform on [exp(min), exp(max)]
"--weight_decay":
hyperdrive.uniform(5e-3, 15e-2),
"--per_device_train_batch_size":
hyperdrive.choice([16, 32]),
}
hyperparameter_sampling = RandomParameterSampling(search_space)
policy = TruncationSelectionPolicy(truncation_percentage=50,
evaluation_interval=2,
delay_evaluation=0)
hyperdrive_config = HyperDriveConfig(
run_config=config,
def build_pipeline(dataset, ws, config):
print("building pipeline for dataset %s in workspace %s" % (dataset, ws.name))
base_dir = '.'
def_blob_store = ws.get_default_datastore()
# folder for scripts that need to be uploaded to Aml compute target
script_folder = './scripts'
os.makedirs(script_folder, exist_ok=True)
shutil.copy(os.path.join(base_dir, 'video_decoding.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'pipelines_submit.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'pipelines_create.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'train.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'data_utils.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'prednet.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'keras_utils.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'data_preparation.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'model_registration.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'config.json'), script_folder)
cpu_compute_name = config['cpu_compute']
try:
cpu_compute_target = AmlCompute(ws, cpu_compute_name)
print("found existing compute target: %s" % cpu_compute_name)
except:# ComputeTargetException:
print("creating new compute target")
provisioning_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_D2_V2',
max_nodes=4,
idle_seconds_before_scaledown=1800)
cpu_compute_target = ComputeTarget.create(ws, cpu_compute_name, provisioning_config)
cpu_compute_target.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)
# use get_status() to get a detailed status for the current cluster.
print(cpu_compute_target.get_status().serialize())
# choose a name for your cluster
gpu_compute_name = config['gpu_compute']
try:
gpu_compute_target = AmlCompute(workspace=ws, name=gpu_compute_name)
print("found existing compute target: %s" % gpu_compute_name)
except:
print('Creating a new compute target...')
provisioning_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6',
max_nodes=10,
idle_seconds_before_scaledown=1800)
# create the cluster
gpu_compute_target = ComputeTarget.create(ws, gpu_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 uses the scale settings for the cluster
gpu_compute_target.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)
# use get_status() to get a detailed status for the current cluster.
try:
print(gpu_compute_target.get_status().serialize())
except BaseException as e:
print("Could not get status of compute target.")
print(e)
# conda dependencies for compute targets
cpu_cd = CondaDependencies.create(conda_packages=["py-opencv=3.4.2"], pip_indexurl='https://azuremlsdktestpypi.azureedge.net/sdk-release/Candidate/604C89A437BA41BD942B4F46D9A3591D', pip_packages=["azure-storage-blob==1.5.0", "hickle==3.4.3", "requests==2.21.0", "sklearn", "pandas==0.24.2", "azureml-sdk", "numpy==1.16.2", "pillow==6.0.0"])
# Runconfigs
cpu_compute_run_config = RunConfiguration(conda_dependencies=cpu_cd)
cpu_compute_run_config.environment.docker.enabled = True
cpu_compute_run_config.environment.docker.gpu_support = False
cpu_compute_run_config.environment.docker.base_image = DEFAULT_CPU_IMAGE
cpu_compute_run_config.environment.spark.precache_packages = False
print("PipelineData object created")
# DataReference to where video data is stored.
video_data = DataReference(
datastore=def_blob_store,
data_reference_name="video_data",
path_on_datastore=os.path.join("prednet", "data", "video", dataset))
print("DataReference object created")
# Naming the intermediate data as processed_data1 and assigning it to the variable processed_data1.
raw_data = PipelineData("raw_video_fames", datastore=def_blob_store)
preprocessed_data = PipelineData("preprocessed_video_frames", datastore=def_blob_store)
data_metrics = PipelineData("data_metrics", datastore=def_blob_store)
data_output = PipelineData("output_data", datastore=def_blob_store)
# prepare dataset for training/testing prednet
video_decoding = PythonScriptStep(
name='decode_videos',
script_name="video_decoding.py",
arguments=["--input_data", video_data, "--output_data", raw_data],
inputs=[video_data],
outputs=[raw_data],
compute_target=cpu_compute_target,
source_directory=script_folder,
runconfig=cpu_compute_run_config,
allow_reuse=True,
hash_paths=['.']
)
print("video_decode step created")
# prepare dataset for training/testing recurrent neural network
data_prep = PythonScriptStep(
name='prepare_data',
script_name="data_preparation.py",
arguments=["--input_data", raw_data, "--output_data", preprocessed_data],
inputs=[raw_data],
outputs=[preprocessed_data],
compute_target=cpu_compute_target,
source_directory=script_folder,
runconfig=cpu_compute_run_config,
allow_reuse=True,
hash_paths=['.']
)
data_prep.run_after(video_decoding)
print("data_prep step created")
# configure access to ACR for pulling our custom docker image
acr = ContainerRegistry()
acr.address = config['acr_address']
acr.username = config['acr_username']
acr.password = config['acr_password']
est = Estimator(source_directory=script_folder,
compute_target=gpu_compute_target,
entry_script='train.py',
use_gpu=True,
node_count=1,
custom_docker_image = "wopauli_1.8-gpu:1",
image_registry_details=acr,
user_managed=True
)
ps = RandomParameterSampling(
{
'--batch_size': choice(1, 2, 4, 8),
'--filter_sizes': choice("3, 3, 3", "4, 4, 4", "5, 5, 5"),
'--stack_sizes': choice("48, 96, 192", "36, 72, 144", "12, 24, 48"), #, "48, 96"),
'--learning_rate': loguniform(-6, -1),
'--lr_decay': loguniform(-9, -1),
'--freeze_layers': choice("0, 1, 2", "1, 2, 3", "0, 1", "1, 2", "2, 3", "0", "3"),
'--transfer_learning': choice("True", "False")
}
)
policy = BanditPolicy(evaluation_interval=2, slack_factor=0.1, delay_evaluation=10)
hdc = HyperDriveConfig(estimator=est,
hyperparameter_sampling=ps,
policy=policy,
primary_metric_name='val_loss',
primary_metric_goal=PrimaryMetricGoal.MINIMIZE,
max_total_runs=10,
max_concurrent_runs=5,
max_duration_minutes=60*6
)
hd_step = HyperDriveStep(
name="train_w_hyperdrive",
hyperdrive_run_config=hdc,
estimator_entry_script_arguments=[
'--data-folder', preprocessed_data,
'--remote_execution',
'--dataset', dataset
],
inputs=[preprocessed_data],
metrics_output = data_metrics,
allow_reuse=True
)
hd_step.run_after(data_prep)
registration_step = PythonScriptStep(
name='register_model',
script_name='model_registration.py',
arguments=['--input_dir', data_metrics, '--output_dir', data_output],
compute_target=cpu_compute_target,
inputs=[data_metrics],
outputs=[data_output],
source_directory=script_folder,
allow_reuse=True,
hash_paths=['.']
)
registration_step.run_after(hd_step)
pipeline = Pipeline(workspace=ws, steps=[video_decoding, data_prep, hd_step, registration_step])
print ("Pipeline is built")
pipeline.validate()
print("Simple validation complete")
pipeline_name = 'prednet_' + dataset
published_pipeline = pipeline.publish(name=pipeline_name)
schedule = Schedule.create(workspace=ws, name=pipeline_name + "_sch",
pipeline_id=published_pipeline.id,
experiment_name=pipeline_name,
datastore=def_blob_store,
wait_for_provisioning=True,
description="Datastore scheduler for Pipeline" + pipeline_name,
path_on_datastore=os.path.join('prednet/data/video', dataset, 'Train'),
polling_interval=1
)
return pipeline_name
'keras', 'tensorflow', 'tensorflow-gpu', 'matplotlib',
'pillow', 'six', 'numpy', 'azureml-sdk', 'tqdm'
],
conda_packages=['cudatoolkit=10.0.130'],
entry_script='kd_squeezenet.py',
use_gpu=True,
node_count=1)
from azureml.train.hyperdrive import RandomParameterSampling, BanditPolicy, HyperDriveConfig, PrimaryMetricGoal
from azureml.pipeline.steps import HyperDriveStep
from azureml.train.hyperdrive import choice, loguniform, uniform
ps = RandomParameterSampling({
'--learning_rate': uniform(1e-3, 2e-2),
'--momentum': uniform(.1, .95),
'--weight_decay': loguniform(-5, -3),
'--temperature': uniform(1, 9),
# '--lambda_const': uniform(.1, .3),
'--transfer_learning': choice("True", "False")
})
policy = BanditPolicy(evaluation_interval=2,
slack_factor=0.1,
delay_evaluation=10)
hdc = HyperDriveConfig(
estimator=est,
hyperparameter_sampling=ps,
policy=policy,
primary_metric_name='val_loss',
primary_metric_goal=PrimaryMetricGoal.MINIMIZE,
# run = exp.submit(est)
# print(run)
# run.wait_for_completion(show_output=True)
ps = RandomParameterSampling({
'--batch_size':
choice(2, 4, 8, 16),
'--filter_sizes':
choice("3 3 3", "4 4 4", "5 5 5"),
'--stack_sizes':
choice("48 96 192", "36 72 144", "12 24 48"),
'--learning_rate':
loguniform(-6, -1),
'--lr_decay':
loguniform(-9, -1)
})
policy = BanditPolicy(evaluation_interval=2,
slack_factor=0.1) #, delay_evaluation=20)
hdc = HyperDriveRunConfig(estimator=est,
hyperparameter_sampling=ps,
policy=policy,
primary_metric_name='val_loss',
primary_metric_goal=PrimaryMetricGoal.MINIMIZE,
max_total_runs=5,
max_concurrent_runs=50)
def build_pipeline(dataset, ws, config):
print("building pipeline for dataset %s in workspace %s" %
(dataset, ws.name))
hostname = socket.gethostname()
if hostname == 'wopauliNC6':
base_dir = '.'
else:
base_dir = '.'
def_blob_store = ws.get_default_datastore()
# folder for scripts that need to be uploaded to Aml compute target
script_folder = './scripts'
os.makedirs(script_folder, exist_ok=True)
shutil.copy(os.path.join(base_dir, 'video_decoding.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'pipelines_submit.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'pipelines_build.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'train.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'data_utils.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'prednet.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'keras_utils.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'data_preparation.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'model_registration.py'), script_folder)
shutil.copy(os.path.join(base_dir, 'config.json'), script_folder)
cpu_compute_name = config['cpu_compute']
try:
cpu_compute_target = AmlCompute(ws, cpu_compute_name)
print("found existing compute target: %s" % cpu_compute_name)
except ComputeTargetException:
print("creating new compute target")
provisioning_config = AmlCompute.provisioning_configuration(
vm_size='STANDARD_D2_V2',
max_nodes=4,
idle_seconds_before_scaledown=1800)
cpu_compute_target = ComputeTarget.create(ws, cpu_compute_name,
provisioning_config)
cpu_compute_target.wait_for_completion(show_output=True,
min_node_count=None,
timeout_in_minutes=20)
# use get_status() to get a detailed status for the current cluster.
print(cpu_compute_target.get_status().serialize())
# choose a name for your cluster
gpu_compute_name = config['gpu_compute']
try:
gpu_compute_target = AmlCompute(workspace=ws, name=gpu_compute_name)
print("found existing compute target: %s" % gpu_compute_name)
except ComputeTargetException:
print('Creating a new compute target...')
provisioning_config = AmlCompute.provisioning_configuration(
vm_size='STANDARD_NC6',
max_nodes=5,
idle_seconds_before_scaledown=1800)
# create the cluster
gpu_compute_target = ComputeTarget.create(ws, gpu_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 uses the scale settings for the cluster
gpu_compute_target.wait_for_completion(show_output=True,
min_node_count=None,
timeout_in_minutes=20)
# use get_status() to get a detailed status for the current cluster.
print(gpu_compute_target.get_status().serialize())
# conda dependencies for compute targets
cpu_cd = CondaDependencies.create(conda_packages=["py-opencv=3.4.2"],
pip_packages=[
"azure-storage-blob==1.5.0",
"hickle==3.4.3", "requests==2.21.0",
"sklearn", "pandas==0.24.2",
"azureml-sdk==1.0.21",
"numpy==1.16.2", "pillow==6.0.0"
])
gpu_cd = CondaDependencies.create(pip_packages=[
"keras==2.0.8", "theano==1.0.4", "tensorflow==1.8.0",
"tensorflow-gpu==1.8.0", "hickle==3.4.3", "matplotlib==3.0.3",
"seaborn==0.9.0", "requests==2.21.0", "bs4==0.0.1", "imageio==2.5.0",
"sklearn", "pandas==0.24.2", "azureml-sdk==1.0.21", "numpy==1.16.2"
])
# Runconfigs
cpu_compute_run_config = RunConfiguration(conda_dependencies=cpu_cd)
cpu_compute_run_config.environment.docker.enabled = True
cpu_compute_run_config.environment.docker.gpu_support = False
cpu_compute_run_config.environment.docker.base_image = DEFAULT_CPU_IMAGE
cpu_compute_run_config.environment.spark.precache_packages = False
gpu_compute_run_config = RunConfiguration(conda_dependencies=gpu_cd)
gpu_compute_run_config.environment.docker.enabled = True
gpu_compute_run_config.environment.docker.gpu_support = True
gpu_compute_run_config.environment.docker.base_image = DEFAULT_GPU_IMAGE
gpu_compute_run_config.environment.spark.precache_packages = False
print("PipelineData object created")
video_data = DataReference(datastore=def_blob_store,
data_reference_name="video_data",
path_on_datastore=os.path.join(
"prednet", "data", "video", dataset))
# Naming the intermediate data as processed_data1 and assigning it to the variable processed_data1.
raw_data = PipelineData("raw_video_fames", datastore=def_blob_store)
preprocessed_data = PipelineData("preprocessed_video_frames",
datastore=def_blob_store)
data_metrics = PipelineData("data_metrics", datastore=def_blob_store)
data_output = PipelineData("output_data", datastore=def_blob_store)
print("DataReference object created")
# prepare dataset for training/testing prednet
video_decoding = PythonScriptStep(
name='decode_videos',
script_name="video_decoding.py",
arguments=["--input_data", video_data, "--output_data", raw_data],
inputs=[video_data],
outputs=[raw_data],
compute_target=cpu_compute_target,
source_directory=script_folder,
runconfig=cpu_compute_run_config,
allow_reuse=True,
hash_paths=['.'])
print("video_decode created")
# prepare dataset for training/testing recurrent neural network
data_prep = PythonScriptStep(name='prepare_data',
script_name="data_preparation.py",
arguments=[
"--input_data", raw_data, "--output_data",
preprocessed_data
],
inputs=[raw_data],
outputs=[preprocessed_data],
compute_target=cpu_compute_target,
source_directory=script_folder,
runconfig=cpu_compute_run_config,
allow_reuse=True,
hash_paths=['.'])
data_prep.run_after(video_decoding)
print("data_prep created")
est = TensorFlow(source_directory=script_folder,
compute_target=gpu_compute_target,
pip_packages=[
'keras==2.0.8', 'theano', 'tensorflow==1.8.0',
'tensorflow-gpu==1.8.0', 'matplotlib', 'horovod',
'hickle'
],
entry_script='train.py',
use_gpu=True,
node_count=1)
ps = RandomParameterSampling({
'--batch_size':
choice(2, 4, 8, 16),
'--filter_sizes':
choice("3, 3, 3", "4, 4, 4", "5, 5, 5"),
'--stack_sizes':
choice("48, 96, 192", "36, 72, 144", "12, 24, 48"), #, "48, 96"),
'--learning_rate':
loguniform(-6, -1),
'--lr_decay':
loguniform(-9, -1),
'--freeze_layers':
choice("0, 1, 2", "1, 2, 3", "0, 1", "1, 2", "2, 3", "0", "1", "2",
"3"),
'--transfer_learning':
choice("True", "False")
})
policy = BanditPolicy(evaluation_interval=2,
slack_factor=0.1,
delay_evaluation=20)
hdc = HyperDriveRunConfig(
estimator=est,
hyperparameter_sampling=ps,
policy=policy,
primary_metric_name='val_loss',
primary_metric_goal=PrimaryMetricGoal.MINIMIZE,
max_total_runs=5, #100,
max_concurrent_runs=5, #10,
max_duration_minutes=60 * 6)
hd_step = HyperDriveStep(name="train_w_hyperdrive",
hyperdrive_run_config=hdc,
estimator_entry_script_arguments=[
'--data-folder', preprocessed_data,
'--remote_execution'
],
inputs=[preprocessed_data],
metrics_output=data_metrics,
allow_reuse=True)
hd_step.run_after(data_prep)
registration_step = PythonScriptStep(
name='register_model',
script_name='model_registration.py',
arguments=['--input_dir', data_metrics, '--output_dir', data_output],
compute_target=gpu_compute_target,
inputs=[data_metrics],
outputs=[data_output],
source_directory=script_folder,
allow_reuse=True,
hash_paths=['.'])
registration_step.run_after(hd_step)
pipeline = Pipeline(
workspace=ws,
steps=[video_decoding, data_prep, hd_step, registration_step])
print("Pipeline is built")
pipeline.validate()
print("Simple validation complete")
pipeline_name = 'prednet_' + dataset
pipeline.publish(name=pipeline_name)
return pipeline_name
print('predictions:\t', y_hat[:30])
print("Accuracy on the test set:", np.average(y_hat == y_test))
from azureml.train.hyperdrive import RandomParameterSampling, BanditPolicy, HyperDriveConfig, PrimaryMetricGoal
from azureml.train.hyperdrive import choice, loguniform
ps = RandomParameterSampling({
'--batch-size':
choice(32, 64, 128),
'--first-layer-neurons':
choice(16, 64, 128, 256, 512),
'--second-layer-neurons':
choice(16, 64, 256, 512),
'--learning-rate':
loguniform(-6, -1)
})
est = TensorFlow(source_directory=script_folder,
script_params={
'--data-folder':
dataset.as_named_input('mnist').as_mount()
},
compute_target=compute_target,
entry_script='tf_mnist2.py',
framework_version='2.0',
use_gpu=True,
pip_packages=['azureml-dataprep[pandas,fuse]'])
policy = BanditPolicy(evaluation_interval=2, slack_factor=0.1)
'keras==2.2.4', 'tensorflow==1.12.0',
'tensorflow-gpu==1.12.0', 'matplotlib', 'horovod',
'hickle', 'pillow==5.1.0', 'six==1.11.0', 'numpy==1.14.5'
],
entry_script='vanilla_squeezenet.py',
use_gpu=True,
node_count=1)
# run = exp.submit(est)
# print(run)
# run.wait_for_completion(show_output=True)
ps = RandomParameterSampling({
'--learning_rate': loguniform(-4, -2),
'--momentum': loguniform(-9, -1),
'--weight_decay': loguniform(-3, -1),
'--transfer_learning': choice("True", "False")
})
policy = BanditPolicy(evaluation_interval=2,
slack_factor=0.1,
delay_evaluation=10)
hdc = HyperDriveRunConfig(estimator=est,
hyperparameter_sampling=ps,
policy=policy,
primary_metric_name='val_loss',
primary_metric_goal=PrimaryMetricGoal.MINIMIZE,
max_total_runs=100,