Developers Guide to AI - Speaker Deck

Slide 1

Slide 1 text

.Developers guide to A.I. . Henk Boelman . Cloud Advocate @ Microsoft HenkBoelman.com . @hboelman .

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

No content

Slide 4

Slide 4 text

No content

Slide 5

Slide 5 text

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?

Slide 6

Slide 6 text

Machine Learning Ability to learn without being explicitly programmed.

Slide 7

Slide 7 text

Programming Algorithm Data Answers

Slide 8

Slide 8 text

Machine Learning Algorithm Data Answers

Slide 9

Slide 9 text

Machine Learning Model Data Answers

Slide 10

Slide 10 text

Machine Learning Model Data Answers

Slide 11

Slide 11 text

Machine Learning Predictions Data Model Data Answers

Slide 12

Slide 12 text

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

Slide 13

Slide 13 text

Computer Vision An AI service that analyses content in images

Slide 14

Slide 14 text

Computer Vision

Slide 15

Slide 15 text

Computer Vision

Slide 16

Slide 16 text

Custom Vision Service An easy-to-use tool for creating your own custom image classifier

Slide 17

Slide 17 text

No content

Slide 18

Slide 18 text

No content

Slide 19

Slide 19 text

No content

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

Demo: Create a Simpsons classifier

Slide 22

Slide 22 text

Demo: Aka.ms/AI4DEV01-CustomVision @hboelman [email protected]

Slide 23

Slide 23 text

Azure Machine Learning studio A fully-managed cloud service that enables you to easily build, deploy, and share predictive analytics solutions.

Slide 24

Slide 24 text

Is it Marge or Homer?

Slide 25

Slide 25 text

No content

Slide 26

Slide 26 text

Prepare your environment Experiment with your model & data Deploy Your model into production

Slide 27

Slide 27 text

Step 1: Prepare your environment

Slide 28

Slide 28 text

Setup your environment VS Code Azure Notebooks Azure Portal

Slide 29

Slide 29 text

No content

Slide 30

Slide 30 text

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

Slide 31

Slide 31 text

Create a workspace ws = Workspace.create( name='', subscription_id='', resource_group='', location='westeurope') ws.write_config() ws = Workspace.from_config() Create a workspace

Slide 32

Slide 32 text

Create Compute cfg = AmlCompute.provisioning_configuration( vm_size='STANDARD_NC6', min_nodes=1, max_nodes=6) cc = ComputeTarget.create(ws, '', cfg) Create a workspace Create compute

Slide 33

Slide 33 text

No content

Slide 34

Slide 34 text

Step 1 Prepare your environment Create a workspace Create compute Setup storage

Slide 35

Slide 35 text

Step 2: Experiment with your model & data

Slide 36

Slide 36 text

Create an experiment exp = Experiment(workspace=ws, name=“”) Create an Experiment

Slide 37

Slide 37 text

Create a training file Create an Experiment Create a training file

Slide 38

Slide 38 text

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

Slide 39

Slide 39 text

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

Slide 40

Slide 40 text

Create an Experiment Create a training file Submit to the AI cluster Create an estimator Demo: Creating and run an experiment

Slide 41

Slide 41 text

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

Slide 42

Slide 42 text

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

Slide 43

Slide 43 text

Create an Experiment Create a training file Submit to the AI cluster Create an estimator Register the model Demo: Register and test the model

Slide 44

Slide 44 text

Demo: Aka.ms/AI4DEV02-amls-basics @hboelman [email protected]

Slide 45

Slide 45 text

Step 3: Deploy Your model into production

Slide 46

Slide 46 text

No content

Slide 47

Slide 47 text

AMLS to deploy The Model Score.py Environment file Docker Image

Slide 48

Slide 48 text

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)

Slide 49

Slide 49 text

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')

Slide 50

Slide 50 text

Inference config inference_config = InferenceConfig( runtime= "python", entry_script="score.py", conda_file="myenv.yml" )

Slide 51

Slide 51 text

Deployment using AMLS

Slide 52

Slide 52 text

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)

Slide 53

Slide 53 text

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)

Slide 54

Slide 54 text

Demo: Deploy to ACI & AKS

Slide 55

Slide 55 text

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?

Slide 56

Slide 56 text

One final thing ..

Slide 57

Slide 57 text

No content

Slide 58

Slide 58 text

“The future we invent is a choice we make, not something that just happens” Satya Nadella

Slide 59

Slide 59 text

@hboelman github.com/hnky henkboelman.com Thank you! Read more on: henkboelman.com

Slide 60

Slide 60 text

“The future we invent is a choice we make, not something that just happens” Satya Nadella

Slide 61

Slide 61 text

No content