For deploying ML models to Azure you need to follow the stages as mentioned <\/p>\n\n\n\n
Pre-requisites for deployment of ML model to Azure<\/strong> <\/p>\n\n\n\n Model registration helps you in storing version of your ML model in your workspace on Azure cloud. The registration of the model is done by the name and the version of the model. It is a good practice to provide extra metadata tags during registration. These tags enable easy searching of the model on Azure. Azure ML supports any model loaded with Python 3.5.2 or higher versions. For registering your model, you need resources like a pytorch model file which can represent the specific model and codes executing the model. <\/p>\n\n\n\n You can register your model from <\/p>\n\n\n\n !wget https:\/\/aka.ms\/bidaf-9-model -o model.onnx <\/p>\n\n\n\n !az ml model register -n bidaf_onnx -p .\/model.onnx <\/p>\n\n\n\n az ml model register -n bidaf_onnx –asset-path outputs\/model.onnx –experiment-name myexperiment –run-id myrunid –tag area=qna <\/p>\n\n\n\n The entry script is required for accepting the requests, scoring the requests with the ML model and returning the result output. Your entry script should enable you to load your model using the (in (it) function and use the input data to run the model with run function <\/p>\n\n\n\n import json <\/p>\n\n\n\n def init(): <\/p>\n\n\n\n print(“This is init”) <\/p>\n\n\n\n def run(data): <\/p>\n\n\n\n test = json.loads(data) <\/p>\n\n\n\n print(f”received data {test}”) <\/p>\n\n\n\n return f”test is {test}” <\/p>\n\n\n\n The inference configuration details the docker containers alongwith files to be used while initialising the web service. The source directory files are pushed to cloud when you start deploying the web service <\/p>\n\n\n\n After this, you are fully prepared to deploy the ML model <\/p>\n\n\n\n !az ml model deploy -n myservice -m model name –overwrite –ic dummyinferenceconfig.json –dc deploymentconfig.json <\/p>\n\n\n\n !az ml service get-logs -n myservice <\/p>\n\n\n\n To ensure that you have deployed the ML model\u00a0successfully ,\u00a0you need to conduct a liveness request and a scoring request\u00a0<\/p>\n\n\n\n !curl -v http:\/\/localhost:32267 <\/p>\n\n\n\n !curl\u00a0-v -X POST -H “content-type:application\/json” -d ‘{“query”: “What\u00a0color\u00a0is the fox”, “context”: “The quick brown fox jumped over the lazy dog.”}’ http:\/\/localhost:32267\/score\u00a0<\/p>\n\n\n\t\t