jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Version 0.1.80

Browse Source
This commit is contained in:
rastala
2018-11-20 11:00:48 -05:00
parent d10b1fa796
commit 5726fe3ddb
61 changed files with 23040 additions and 24681 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1612
training/01.train-hyperparameter-tune-deploy-with-pytorch/01.train-hyperparameter-tune-deploy-with-pytorch.ipynb
View File

File diff suppressed because it is too large Load Diff

40
training/01.train-hyperparameter-tune-deploy-with-pytorch/pytorch_score.py
View File

@@ -5,35 +5,10 @@ import torch
import torch.nn as nn
from torchvision import transforms
import json
import base64
from io import BytesIO
from PIL import Image
from azureml.core.model import Model
def preprocess_image(image_file):
"""Preprocess the input image."""
data_transforms = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
image = Image.open(image_file)
image = data_transforms(image).float()
image = torch.tensor(image)
image = image.unsqueeze(0)
return image
def base64ToImg(base64ImgString):
base64Img = base64ImgString.encode('utf-8')
decoded_img = base64.b64decode(base64Img)
return BytesIO(decoded_img)
def init():
global model
model_path = Model.get_model_path('pytorch-hymenoptera')
@@ -42,16 +17,15 @@ def init():
def run(input_data):
img = base64ToImg(json.loads(input_data)['data'])
img = preprocess_image(img)
input_data = torch.tensor(json.loads(input_data)['data'])
# get prediction
output = model(img)
classes = ['ants', 'bees']
softmax = nn.Softmax(dim=1)
pred_probs = softmax(model(img)).detach().numpy()[0]
index = torch.argmax(output, 1)
with torch.no_grad():
output = model(input_data)
classes = ['ants', 'bees']
softmax = nn.Softmax(dim=1)
pred_probs = softmax(output).numpy()[0]
index = torch.argmax(output, 1)
result = {"label": classes[index], "probability": str(pred_probs[index])}
return result

22
training/01.train-hyperparameter-tune-deploy-with-pytorch/pytorch_train.py
View File

@@ -59,6 +59,7 @@ def train_model(model, criterion, optimizer, scheduler, num_epochs, data_dir):
dataloaders, dataset_sizes, class_names = load_data(data_dir)
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
since = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
@@ -146,12 +147,15 @@ def fine_tune_model(num_epochs, data_dir, learning_rate, momentum):
criterion = nn.CrossEntropyLoss()
# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=learning_rate, momentum=momentum)
optimizer_ft = optim.SGD(model_ft.parameters(),
lr=learning_rate, momentum=momentum)
# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
exp_lr_scheduler = lr_scheduler.StepLR(
optimizer_ft, step_size=7, gamma=0.1)
model = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs, data_dir)
model = train_model(model_ft, criterion, optimizer_ft,
exp_lr_scheduler, num_epochs, data_dir)
return model
@@ -159,15 +163,19 @@ def fine_tune_model(num_epochs, data_dir, learning_rate, momentum):
def main():
# get command-line arguments
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str, help='directory of training data')
parser.add_argument('--num_epochs', type=int, default=25, help='number of epochs to train')
parser.add_argument('--data_dir', type=str,
help='directory of training data')
parser.add_argument('--num_epochs', type=int, default=25,
help='number of epochs to train')
parser.add_argument('--output_dir', type=str, help='output directory')
parser.add_argument('--learning_rate', type=float, default=0.001, help='learning rate')
parser.add_argument('--learning_rate', type=float,
default=0.001, help='learning rate')
parser.add_argument('--momentum', type=float, default=0.9, help='momentum')
args = parser.parse_args()
print("data directory is: " + args.data_dir)
model = fine_tune_model(args.num_epochs, args.data_dir, args.learning_rate, args.momentum)
model = fine_tune_model(args.num_epochs, args.data_dir,
args.learning_rate, args.momentum)
os.makedirs(args.output_dir, exist_ok=True)
torch.save(model, os.path.join(args.output_dir, 'model.pt'))

624
training/02.distributed-pytorch-with-horovod/02.distributed-pytorch-with-horovod.ipynb
View File

@@ -1,315 +1,313 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 02. Distributed PyTorch with Horovod\n",
"In this tutorial, you will train a PyTorch model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-pytorch) on single-node PyTorch training using the SDK"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"\n",
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target.')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_max_nodes=4)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
" compute_target.wait_for_completion(show_output=True)\n",
"\n",
" # Use the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster ready to go, let's run our distributed training job."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"project_folder = './pytorch-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `pytorch_horovod_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('pytorch_horovod_mnist.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed PyTorch tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'pytorch-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a PyTorch estimator\n",
"The AML SDK's PyTorch estimator enables you to easily submit PyTorch training jobs for both single-node and distributed runs. For more information on the PyTorch estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-pytorch)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import PyTorch\n",
"\n",
"estimator = PyTorch(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='pytorch_horovod_mnist.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, PyTorch, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `PyTorch` constructor's `pip_packages` or `conda_packages` parameters."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run.get_details())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"authors": [
{
"name": "minxia"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
},
"msauthor": "minxia"
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
"nbformat": 4,
"nbformat_minor": 2
}
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 02. Distributed PyTorch with Horovod\n",
"In this tutorial, you will train a PyTorch model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-pytorch) on single-node PyTorch training using the SDK"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"\n",
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target.')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" max_nodes=6)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
"compute_target.wait_for_completion(show_output=True)\n",
"\n",
"# Use the 'status' property to get a detailed status for the current cluster. \n",
"print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster ready to go, let's run our distributed training job."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"project_folder = './pytorch-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `pytorch_horovod_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('pytorch_horovod_mnist.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed PyTorch tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'pytorch-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a PyTorch estimator\n",
"The AML SDK's PyTorch estimator enables you to easily submit PyTorch training jobs for both single-node and distributed runs. For more information on the PyTorch estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-pytorch)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import PyTorch\n",
"\n",
"estimator = PyTorch(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='pytorch_horovod_mnist.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, PyTorch, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `PyTorch` constructor's `pip_packages` or `conda_packages` parameters."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run.get_details())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"authors": [
{
"name": "minxia"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
},
"msauthor": "minxia"
},
"nbformat": 4,
"nbformat_minor": 2
}

1624
training/03.train-hyperparameter-tune-deploy-with-tensorflow/.ipynb_checkpoints/03.train-hyperparameter-tune-deploy-with-tensorflow-checkpoint.ipynb
View File

File diff suppressed because it is too large Load Diff

2838
training/03.train-hyperparameter-tune-deploy-with-tensorflow/03.train-hyperparameter-tune-deploy-with-tensorflow.ipynb
View File

File diff suppressed because it is too large Load Diff

2
training/03.train-hyperparameter-tune-deploy-with-tensorflow/tf_mnist.py
View File

@@ -39,7 +39,7 @@ n_h1 = args.n_hidden_1
n_h2 = args.n_hidden_2
n_outputs = 10
learning_rate = args.learning_rate
n_epochs = 50
n_epochs = 20
batch_size = args.batch_size
with tf.name_scope('network'):

782
training/04.distributed-tensorflow-with-horovod/04.distributed-tensorflow-with-horovod.ipynb
View File

@@ -1,386 +1,400 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 04. Distributed Tensorflow with Horovod\n",
"In this tutorial, you will train a word2vec model in TensorFlow using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_max_nodes=4)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
" compute_target.wait_for_completion(show_output=True)\n",
"\n",
" # Use the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload data to datastore\n",
"To make data accessible for remote training, AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data to Azure Storage, and interact with it from your remote compute targets. \n",
"\n",
"If your data is already stored in Azure, or you download the data as part of your training script, you will not need to do this step. For this tutorial, although you can download the data in your training script, we will demonstrate how to upload the training data to a datastore and access it during training to illustrate the datastore functionality."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, download the training data from [here](http://mattmahoney.net/dc/text8.zip) to your local machine:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import urllib\n",
"\n",
"os.makedirs('./data', exist_ok=True)\n",
"download_url = 'http://mattmahoney.net/dc/text8.zip'\n",
"urllib.request.urlretrieve(download_url, filename='./data/text8.zip')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore. The below code will upload the contents of the data directory to the path `./data` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)\n",
"\n",
"ds.upload(src_dir='data', target_path='data', overwrite=True, show_progress=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For convenience, let's get a reference to the path on the datastore with the zip file of training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--input_data` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'data/text8.zip'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script, and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"project_folder = './tf-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_horovod_word2vec.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_horovod_word2vec.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--input_data': ds_data\n",
"}\n",
"\n",
"estimator= TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_horovod_word2vec.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, TensorFlow, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters.\n",
"\n",
"Note that we passed our training data reference `ds_data` to our script's `--input_data` argument. This will 1) mount our datastore on the remote compute and 2) provide the path to the data zip file on our datastore."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"authors": [
{
"name": "roastala"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
},
"msauthor": "minxia"
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
"nbformat": 4,
"nbformat_minor": 2
}
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 04. Distributed Tensorflow with Horovod\n",
"In this tutorial, you will train a word2vec model in TensorFlow using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" max_nodes=6)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
"compute_target.wait_for_completion(show_output=True)\n",
"\n",
"# Use the 'status' property to get a detailed status for the current cluster. \n",
"print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload data to datastore\n",
"To make data accessible for remote training, AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data to Azure Storage, and interact with it from your remote compute targets. \n",
"\n",
"If your data is already stored in Azure, or you download the data as part of your training script, you will not need to do this step. For this tutorial, although you can download the data in your training script, we will demonstrate how to upload the training data to a datastore and access it during training to illustrate the datastore functionality."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, download the training data from [here](http://mattmahoney.net/dc/text8.zip) to your local machine:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import urllib\n",
"\n",
"os.makedirs('./data', exist_ok=True)\n",
"download_url = 'http://mattmahoney.net/dc/text8.zip'\n",
"urllib.request.urlretrieve(download_url, filename='./data/text8.zip')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Upload the contents of the data directory to the path `./data` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds.upload(src_dir='data', target_path='data', overwrite=True, show_progress=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For convenience, let's get a reference to the path on the datastore with the zip file of training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--input_data` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'data/text8.zip'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script, and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"project_folder = './tf-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_horovod_word2vec.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_horovod_word2vec.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--input_data': ds_data\n",
"}\n",
"\n",
"estimator= TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_horovod_word2vec.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, TensorFlow, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters.\n",
"\n",
"Note that we passed our training data reference `ds_data` to our script's `--input_data` argument. This will 1) mount our datastore on the remote compute and 2) provide the path to the data zip file on our datastore."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"authors": [
{
"name": "roastala"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
},
"msauthor": "minxia"
},
"nbformat": 4,
"nbformat_minor": 2
}

621
training/05.distributed-tensorflow-with-parameter-server/05.distributed-tensorflow-with-parameter-server.ipynb
View File

@@ -1,313 +1,312 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 05. Distributed TensorFlow with parameter server\n",
"In this tutorial, you will train a TensorFlow model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using native [distributed TensorFlow](https://www.tensorflow.org/deploy/distributed)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target.')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_max_nodes=4)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
" compute_target.wait_for_completion(show_output=True)\n",
"\n",
" # Use the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster ready to go, let's run our distributed training job."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script, and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"project_folder = './tf-distr-ps'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_mnist_replica.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_mnist_replica.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-ps'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--num_gpus': 1\n",
"}\n",
"\n",
"estimator = TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_mnist_replica.py',\n",
" node_count=2,\n",
" worker_count=2,\n",
" parameter_server_count=1, \n",
" distributed_backend='ps',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with two workers and one parameter server. In order to execute a native distributed TensorFlow run, you must provide the argument `distributed_backend='ps'`. Using this estimator with these settings, TensorFlow and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run.get_details())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"authors": [
{
"name": "minxia"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
},
"msauthor": "minxia"
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
"nbformat": 4,
"nbformat_minor": 2
}
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 05. Distributed TensorFlow with parameter server\n",
"In this tutorial, you will train a TensorFlow model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using native [distributed TensorFlow](https://www.tensorflow.org/deploy/distributed)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target.')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" max_nodes=6)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
"compute_target.wait_for_completion(show_output=True)\n",
"\n",
"# Use the 'status' property to get a detailed status for the current cluster. \n",
"print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster ready to go, let's run our distributed training job."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script, and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"project_folder = './tf-distr-ps'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_mnist_replica.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_mnist_replica.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-ps'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--num_gpus': 1,\n",
" '--train_steps': 500\n",
"}\n",
"\n",
"estimator = TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_mnist_replica.py',\n",
" node_count=2,\n",
" worker_count=2,\n",
" parameter_server_count=1, \n",
" distributed_backend='ps',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with two workers and one parameter server. In order to execute a native distributed TensorFlow run, you must provide the argument `distributed_backend='ps'`. Using this estimator with these settings, TensorFlow and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"authors": [
{
"name": "minxia"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
},
"msauthor": "minxia"
},
"nbformat": 4,
"nbformat_minor": 2
}

776
training/06.distributed-cntk-with-custom-docker/06.distributed-cntk-with-custom-docker.ipynb
View File

@@ -1,391 +1,389 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 06. Distributed CNTK using custom docker images\n",
"In this tutorial, you will train a CNTK model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using a custom docker image and distributed training."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
"* Go through the [00.configuration.ipynb]() notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"\n",
"Initialize a [Workspace](https://review.docs.microsoft.com/en-us/azure/machine-learning/service/concept-azure-machine-learning-architecture?branch=release-ignite-aml#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target.')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_max_nodes=4)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
" compute_target.wait_for_completion(show_output=True)\n",
"\n",
" # Use the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload training data\n",
"For this tutorial, we will be using the MNIST dataset.\n",
"\n",
"First, let's download the dataset. We've included the `install_mnist.py` script to download the data and convert it to a CNTK-supported format. Our data files will get written to a directory named `'mnist'`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import install_mnist\n",
"\n",
"install_mnist.main('mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To make the data accessible for remote training, you will need to upload the data from your local machine to the cloud. AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data, and interact with it from your remote compute targets. \n",
"\n",
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore, which we will then mount on the remote compute for training in the next section."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The following code will upload the training data to the path `./mnist` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds.upload(src_dir='./mnist', target_path='./mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now let's get a reference to the path on the datastore with the training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--data_dir` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'mnist'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster ready to go, let's run our distributed training job."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script, and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"project_folder = './cntk-distr'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `cntk_distr_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('cntk_distr_mnist.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed CNTK tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'cntk-distr'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an Estimator\n",
"The AML SDK's base Estimator enables you to easily submit custom scripts for both single-node and distributed runs. You should this generic estimator for training code using frameworks such as sklearn or CNTK that don't have corresponding custom estimators. For more information on using the generic estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-ml-models)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.estimator import *\n",
"\n",
"script_params = {\n",
" '--num_epochs': 50,\n",
" '--data_dir': ds_data.as_mount(),\n",
" '--output_dir': './outputs'\n",
"}\n",
"\n",
"estimator = Estimator(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='cntk_distr_mnist.py',\n",
" script_params=script_params,\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi', \n",
" pip_packages=['cntk-gpu==2.6'],\n",
" custom_docker_base_image='microsoft/mmlspark:gpu-0.12',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We would like to train our model using a [pre-built Docker container](https://hub.docker.com/r/microsoft/mmlspark/). To do so, specify the name of the docker image to the argument `custom_docker_base_image`. You can only provide images available in public docker repositories such as Docker Hub using this argument. To use an image from a private docker repository, use the constructor's `environment_definition` parameter instead. Finally, we provide the `cntk` package to `pip_packages` to install CNTK 2.6 on our custom image.\n",
"\n",
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to run distributed CNTK, which uses MPI, you must provide the argument `distributed_backend='mpi'`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run.get_details())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"authors": [
{
"name": "minxia"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
}
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
"nbformat": 4,
"nbformat_minor": 2
}
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 06. Distributed CNTK using custom docker images\n",
"In this tutorial, you will train a CNTK model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using a custom docker image and distributed training."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
"* Go through the [00.configuration.ipynb]() notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"Diagnostics"
]
},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize workspace\n",
"\n",
"Initialize a [Workspace](https://review.docs.microsoft.com/en-us/azure/machine-learning/service/concept-azure-machine-learning-architecture?branch=release-ignite-aml#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.workspace import Workspace\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\n",
"\n",
"try:\n",
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
" print('Found existing compute target.')\n",
"except ComputeTargetException:\n",
" print('Creating a new compute target...')\n",
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" max_nodes=6)\n",
"\n",
" # create the cluster\n",
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
"\n",
"compute_target.wait_for_completion(show_output=True)\n",
"\n",
"# Use the 'status' property to get a detailed status for the current cluster. \n",
"print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload training data\n",
"For this tutorial, we will be using the MNIST dataset.\n",
"\n",
"First, let's download the dataset. We've included the `install_mnist.py` script to download the data and convert it to a CNTK-supported format. Our data files will get written to a directory named `'mnist'`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import install_mnist\n",
"\n",
"install_mnist.main('mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To make the data accessible for remote training, you will need to upload the data from your local machine to the cloud. AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data, and interact with it from your remote compute targets. \n",
"\n",
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore, which we will then mount on the remote compute for training in the next section."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The following code will upload the training data to the path `./mnist` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds.upload(src_dir='./mnist', target_path='./mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now let's get a reference to the path on the datastore with the training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--data_dir` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'mnist'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster ready to go, let's run our distributed training job."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a project directory\n",
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script, and any additional files your training script depends on."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"project_folder = './cntk-distr'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `cntk_distr_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('cntk_distr_mnist.py', project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an experiment\n",
"Create an [experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed CNTK tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'cntk-distr'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an Estimator\n",
"The AML SDK's base Estimator enables you to easily submit custom scripts for both single-node and distributed runs. You should this generic estimator for training code using frameworks such as sklearn or CNTK that don't have corresponding custom estimators. For more information on using the generic estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-ml-models)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.estimator import *\n",
"\n",
"script_params = {\n",
" '--num_epochs': 20,\n",
" '--data_dir': ds_data.as_mount(),\n",
" '--output_dir': './outputs'\n",
"}\n",
"\n",
"estimator = Estimator(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='cntk_distr_mnist.py',\n",
" script_params=script_params,\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi', \n",
" pip_packages=['cntk-gpu==2.6'],\n",
" custom_docker_base_image='microsoft/mmlspark:gpu-0.12',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We would like to train our model using a [pre-built Docker container](https://hub.docker.com/r/microsoft/mmlspark/). To do so, specify the name of the docker image to the argument `custom_docker_base_image`. You can only provide images available in public docker repositories such as Docker Hub using this argument. To use an image from a private docker repository, use the constructor's `environment_definition` parameter instead. Finally, we provide the `cntk` package to `pip_packages` to install CNTK 2.6 on our custom image.\n",
"\n",
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to run distributed CNTK, which uses MPI, you must provide the argument `distributed_backend='mpi'`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit job\n",
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run = experiment.submit(estimator)\n",
"print(run.get_details())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Monitor your run\n",
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"authors": [
{
"name": "minxia"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

1056
training/07.tensorboard/07.tensorboard.ipynb
View File

File diff suppressed because it is too large Load Diff

492
training/08.export-run-history-to-tensorboard/08.export-run-history-to-tensorboard.ipynb
View File

@@ -1,248 +1,248 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 41. Export Run History as Tensorboard logs\n",
"\n",
"1. Run some training and log some metrics into Run History\n",
"2. Export the run history to some directory as Tensorboard logs\n",
"3. Launch a local Tensorboard to view the run history"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.configuration.ipynb) Notebook first if you haven't."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize Workspace\n",
"\n",
"Initialize a workspace object from persisted configuration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Workspace, Run, Experiment\n",
"\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Set experiment name and start the run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'export-to-tensorboard'\n",
"exp = Experiment(ws, experiment_name)\n",
"root_run = exp.start_logging()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load diabetes dataset, a well-known built-in small dataset that comes with scikit-learn\n",
"from sklearn.datasets import load_diabetes\n",
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"X, y = load_diabetes(return_X_y=True)\n",
"\n",
"columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\n",
"\n",
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
"data = {\n",
" \"train\":{\"x\":x_train, \"y\":y_train}, \n",
" \"test\":{\"x\":x_test, \"y\":y_test}\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Example experiment\n",
"from tqdm import tqdm\n",
"\n",
"alphas = [.1, .2, .3, .4, .5, .6 , .7]\n",
"\n",
"# try a bunch of alpha values in a Linear Regression (Ridge) model\n",
"for alpha in tqdm(alphas):\n",
" # create a bunch of child runs\n",
" with root_run.child_run(\"alpha\" + str(alpha)) as run:\n",
" # More data science stuff\n",
" reg = Ridge(alpha=alpha)\n",
" reg.fit(data[\"train\"][\"x\"], data[\"train\"][\"y\"])\n",
" # TODO save model\n",
" preds = reg.predict(data[\"test\"][\"x\"])\n",
" mse = mean_squared_error(preds, data[\"test\"][\"y\"])\n",
" # End train and eval\n",
"\n",
" # log alpha, mean_squared_error and feature names in run history\n",
" root_run.log(\"alpha\", alpha)\n",
" root_run.log(\"mse\", mse)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Export Run History to Tensorboard logs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Export Run History to Tensorboard logs\n",
"from azureml.contrib.tensorboard.export import export_to_tensorboard\n",
"import os\n",
"import tensorflow as tf\n",
"\n",
"logdir = 'exportedTBlogs'\n",
"log_path = os.path.join(os.getcwd(), logdir)\n",
"try:\n",
" os.stat(log_path)\n",
"except os.error:\n",
" os.mkdir(log_path)\n",
"print(logdir)\n",
"\n",
"# export run history for the project\n",
"export_to_tensorboard(root_run, logdir)\n",
"\n",
"# or export a particular run\n",
"# export_to_tensorboard(run, logdir)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"root_run.complete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Start Tensorboard\n",
"\n",
"Or you can start the Tensorboard outside this notebook to view the result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.tensorboard import Tensorboard\n",
"\n",
"# The Tensorboard constructor takes an array of runs, so be sure and pass it in as a single-element array here\n",
"tb = Tensorboard([], local_root=logdir, port=6006)\n",
"\n",
"# If successful, start() returns a string with the URI of the instance.\n",
"tb.start()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Stop Tensorboard\n",
"\n",
"When you're done, make sure to call the `stop()` method of the Tensorboard object."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tb.stop()"
]
}
],
"metadata": {
"authors": [
{
"name": "roastala"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n",
"Licensed under the MIT License."
]
},
"nbformat": 4,
"nbformat_minor": 2
}
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 41. Export Run History as Tensorboard logs\n",
"\n",
"1. Run some training and log some metrics into Run History\n",
"2. Export the run history to some directory as Tensorboard logs\n",
"3. Launch a local Tensorboard to view the run history"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.configuration.ipynb) Notebook first if you haven't."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check core SDK version number\n",
"import azureml.core\n",
"\n",
"print(\"SDK version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize Workspace\n",
"\n",
"Initialize a workspace object from persisted configuration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Workspace, Run, Experiment\n",
"\n",
"\n",
"ws = Workspace.from_config()\n",
"print('Workspace name: ' + ws.name, \n",
" 'Azure region: ' + ws.location, \n",
" 'Subscription id: ' + ws.subscription_id, \n",
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Set experiment name and start the run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'export-to-tensorboard'\n",
"exp = Experiment(ws, experiment_name)\n",
"root_run = exp.start_logging()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load diabetes dataset, a well-known built-in small dataset that comes with scikit-learn\n",
"from sklearn.datasets import load_diabetes\n",
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"X, y = load_diabetes(return_X_y=True)\n",
"\n",
"columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\n",
"\n",
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
"data = {\n",
" \"train\":{\"x\":x_train, \"y\":y_train}, \n",
" \"test\":{\"x\":x_test, \"y\":y_test}\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Example experiment\n",
"from tqdm import tqdm\n",
"\n",
"alphas = [.1, .2, .3, .4, .5, .6 , .7]\n",
"\n",
"# try a bunch of alpha values in a Linear Regression (Ridge) model\n",
"for alpha in tqdm(alphas):\n",
" # create a bunch of child runs\n",
" with root_run.child_run(\"alpha\" + str(alpha)) as run:\n",
" # More data science stuff\n",
" reg = Ridge(alpha=alpha)\n",
" reg.fit(data[\"train\"][\"x\"], data[\"train\"][\"y\"])\n",
" # TODO save model\n",
" preds = reg.predict(data[\"test\"][\"x\"])\n",
" mse = mean_squared_error(preds, data[\"test\"][\"y\"])\n",
" # End train and eval\n",
"\n",
" # log alpha, mean_squared_error and feature names in run history\n",
" root_run.log(\"alpha\", alpha)\n",
" root_run.log(\"mse\", mse)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Export Run History to Tensorboard logs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Export Run History to Tensorboard logs\n",
"from azureml.contrib.tensorboard.export import export_to_tensorboard\n",
"import os\n",
"import tensorflow as tf\n",
"\n",
"logdir = 'exportedTBlogs'\n",
"log_path = os.path.join(os.getcwd(), logdir)\n",
"try:\n",
" os.stat(log_path)\n",
"except os.error:\n",
" os.mkdir(log_path)\n",
"print(logdir)\n",
"\n",
"# export run history for the project\n",
"export_to_tensorboard(root_run, logdir)\n",
"\n",
"# or export a particular run\n",
"# export_to_tensorboard(run, logdir)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"root_run.complete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Start Tensorboard\n",
"\n",
"Or you can start the Tensorboard outside this notebook to view the result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.tensorboard import Tensorboard\n",
"\n",
"# The Tensorboard constructor takes an array of runs, so be sure and pass it in as a single-element array here\n",
"tb = Tensorboard([], local_root=logdir, port=6006)\n",
"\n",
"# If successful, start() returns a string with the URI of the instance.\n",
"tb.start()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Stop Tensorboard\n",
"\n",
"When you're done, make sure to call the `stop()` method of the Tensorboard object."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tb.stop()"
]
}
],
"metadata": {
"authors": [
{
"name": "roastala"
}
],
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
"name": "python36"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}