Build and deploy PyTorch models with Azure Machine Learning

Transcript

1. Henk Boelman Cloud Advocate @ Microsoft Build and Deploy PyTorch Models with Azure Machine Learning HenkBoelman.com @hboelman
2. Azure Machine Learning studio A fully-managed cloud service that enables you to easily build, deploy, and share predictive analytics solutions.
3. What is Azure Machine Learning? Set of Azure Cloud Services Python SDK Azure CLI Web interface ✓Prepare Data ✓Build Models ✓Train Models ✓Manage Models ✓Track Experiments ✓Deploy Models That enables you to:
4. Is it Marge or Homer or .. or ..?
5. Simpson Lego dataset https://github.com/hnky/dataset-lego-figures
6. Sophisticated pretrained models To simplify solution development Azure Databricks Machine Learning VMs Popular frameworks To build advanced deep learning solutions TensorFlow Keras Pytorch Onnx Azure Machine Learning Language Speech … Azure Search Vision On-premises Cloud Edge Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Flexible deployment To deploy and manage models on intelligent cloud and edge Machine Learning on Azure Cognitive Services
8. Prepare your environment Experiment with your model & data Deploy Your model into production
9. Step 1: Prepare your environment
10. Setup your environment VS Code Python SDK Azure Portal
11. Create a workspace ws = Workspace.create( name='<NAME>', subscription_id='<SUBSCRIPTION ID>', resource_group='<RESOURCE GROUP>', location='westeurope') ws.write_config() ws = Workspace.from_config() Create a workspace
13. Datasets – registered, known data sets Experiments – Training runs Models – Registered, versioned models Endpoints: Real-time Endpoints – Deployed model endpoints Pipeline Endpoints – Training workflows Compute – Managed compute Datastores – Connections to data Azure Machine Learning Service
14. Create Compute cfg = AmlCompute.provisioning_configuration( vm_size='STANDARD_NC6', min_nodes=1, max_nodes=6) cc = ComputeTarget.create(ws, '<NAME>', cfg) Create a workspace Create compute
16. Demo: Setup your workspace Create a workspace Create compute Setup storage
17. Step 1 Prepare your environment Create a workspace Create compute Setup storage
18. Step 2: Experiment with your model & data
19. Create an experiment exp = Experiment(workspace=ws, name=“<ExperimentName>”) Create an Experiment
20. Create a training file Create an Experiment Create a training file
21. Create an estimator params = {'--data-folder': ws.get_default_datastore().as_mount()} estimator = TensorFlow( source_directory = script_folder, script_params = params, compute_target = computeCluster, entry_script = 'train.py’, use_gpu = True, conda_packages = ['scikit-learn','keras','opencv’], framework_version='1.10') Create an Experiment Create a training file Create an estimator
22. Submit the experiment to the cluster run = exp.submit(estimator) RunDetails(run).show() Create an Experiment Create a training file Submit to the AI cluster Create an estimator
23. Create an Experiment Create a training file Submit to the AI cluster Create an estimator Demo: Creating and run an experiment
24. Azure Notebook Compute Target Experiment Docker Image Data store 1. Snapshot folder and send to experiment 2. create docker image 3. Deploy docker and snapshot to compute 4. Mount datastore to compute 6. Stream stdout, logs, metrics 5. Launch the script 7. Copy over outputs
25. Register the model model = run.register_model( model_name='SimpsonsAI', model_path='outputs') Create an Experiment Create a training file Submit to the AI cluster Create an estimator Register the model
26. Create an Experiment Create a training file Submit to the AI cluster Create an estimator Register the model Demo: Register and test the model
27. Step 2 Experiment with your model & data
28. Step 3: Deploy your model into production
29. AMLS to deploy The Model Score.py Environment file Docker Image
30. Score.py %%writefile score.py from azureml.core.model import Model def init(): model_root = Model.get_model_path('MyModel’) loaded_model = model_from_json(loaded_model_json) loaded_model.load_weights(model_file_h5) def run(raw_data): url = json.loads(raw_data)['url’] image_data = cv2.resize(image_data,(96,96)) predicted_labels = loaded_model.predict(data1) return json.dumps(predicted_labels)
31. Environment File from azureml.core.runconfig import CondaDependencies cd = CondaDependencies.create() cd.add_conda_package('keras==2.2.2') cd.add_conda_package('opencv') cd.add_tensorflow_conda_package() cd.save_to_file(base_directory='./', conda_file_path='myenv.yml')
32. Inference config inference_config = InferenceConfig( runtime= "python", entry_script="score.py", conda_file="myenv.yml" )
33. Deployment using AMLS
34. Deploy to ACI aciconfig = AciWebservice.deploy_configuration( cpu_cores = 1, memory_gb = 2) service = Model.deploy(workspace=ws, name='simpsons-aci', models=[model], inference_config=inference_config, deployment_config=aciconfig)
35. Demo: Deploy to ACI
37. @hboelman github.com/hnky henkboelman.com Thank you! Read more on: henkboelman.com