Developers Guide to AI

Transcript

1. .Developers guide to A.I. . Henk Boelman . Cloud Advocate @ Microsoft HenkBoelman.com . @hboelman .
5. In this talk Computer Vision Custom Vision Azure Machine Learning Just call an API Bring your own data Build your own model Is it Marge or Homer?
6. Machine Learning Ability to learn without being explicitly programmed.
7. Programming Algorithm Data Answers
8. Machine Learning Algorithm Data Answers
9. Machine Learning Model Data Answers
10. Machine Learning Model Data Answers
11. Machine Learning Predictions Data Model Data Answers
12. Machine Learning on Azure Domain specific pretrained models To reduce time to market Azure Databricks Machine Learning VMs Popular frameworks To build advanced deep learning solutions TensorFlow Pytorch Onnx Azure Machine Learning Language Speech … Search Vision Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Scikit-Learn PyCharm Jupyter Familiar Data Science tools To simplify model development Visual Studio Code Command line CPU GPU FPGA From the Intelligent Cloud to the Intelligent Edge
13. Computer Vision An AI service that analyses content in images
14. Computer Vision
15. Computer Vision
16. Custom Vision Service An easy-to-use tool for creating your own custom image classifier
21. Demo: Create a Simpsons classifier
22. Demo: Aka.ms/AI4DEV01-CustomVision @hboelman Henk.boelman@microsoft.com
23. Azure Machine Learning studio A fully-managed cloud service that enables you to easily build, deploy, and share predictive analytics solutions.
24. Is it Marge or Homer?
26. Prepare your environment Experiment with your model & data Deploy Your model into production
27. Step 1: Prepare your environment
28. Setup your environment VS Code Azure Notebooks Azure Portal
30. Datasets – registered, known data sets Experiments – Training runs Pipelines – Workflows 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
31. 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
32. 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
34. Step 1 Prepare your environment Create a workspace Create compute Setup storage
35. Step 2: Experiment with your model & data
36. Create an experiment exp = Experiment(workspace=ws, name=“<ExperimentName>”) Create an Experiment
37. Create a training file Create an Experiment Create a training file
38. 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
39. 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
40. Create an Experiment Create a training file Submit to the AI cluster Create an estimator Demo: Creating and run an experiment
41. 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
42. 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
43. Create an Experiment Create a training file Submit to the AI cluster Create an estimator Register the model Demo: Register and test the model
44. Demo: Aka.ms/AI4DEV02-amls-basics @hboelman Henk.boelman@microsoft.com
45. Step 3: Deploy Your model into production
47. AMLS to deploy The Model Score.py Environment file Docker Image
48. 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)
49. 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')
50. Inference config inference_config = InferenceConfig( runtime= "python", entry_script="score.py", conda_file="myenv.yml" )
51. Deployment using AMLS
52. 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)
53. Deploy to AKS aks_target = AksCompute(ws,"AI-AKS-DEMO") deployment_config = AksWebservice.deploy_configuration( cpu_cores = 1, memory_gb = 1) service = Model.deploy(workspace=ws, name="simpsons-ailive", models=[model], inference_config=inference_config, deployment_config=deployment_config, deployment_target=aks_target) service.wait_for_deployment(show_output = True)
54. Demo: Deploy to ACI & AKS
55. Recap Computer Vision Custom Vision Azure Machine Learning Just call an API Bring your own data Build your own model Is it Marge or Homer?
56. One final thing ..
58. “The future we invent is a choice we make, not something that just happens” Satya Nadella
59. @hboelman github.com/hnky henkboelman.com Thank you! Read more on: henkboelman.com
60. “The future we invent is a choice we make, not something that just happens” Satya Nadella