Quick-start: PrimeHub Deploy
Brief
In this quick-start we will learn how to deploy an prepared model file with TensorFlow2 server by Model Deployment. It demonstrates the way of using model URI with an specific image of pre-package server that it integrates the model file into a new image and deploys that image as a service.
- Models is a feature of PrimeHub Enterprise and PrimeHub Deploy.
What we need?
- Choose a group with enabled Model Deployment
- Model file URI:
gs://primehub-models/tensorflow2/mnist
- TensorFlow2 server (built-in)
- An instance type >= minimal requirement (CPU=0.5, GPU=0, Mem=1G)
Please have the instance type on PrimeHub or request administrators for the assistance before we start.
Deploy Model file with TensorFlow2 Server
Enter Models from User Portal and create a Deployment.
Fill in Deployment name with
tensorflow2-mnist
Select
TensorFlow2 server
in Model Image fieldFill in Model URI with
gs://primehub-models/tensorflow2/mnist
Click Deploy to start the deployment. We can see the created deployment in orange which indicates Deploying status.
Click Refresh until the deployment turning to green which indicates Deployed and Serving.
Click the deployment to view the detailed information.
Copy Endpoint URL where our service locates and replace
${YOUR_ENDPOINT_URL}
in command below. Run it in terminal to send a testing POST request against the endpoint.curl -X POST ${YOUR_ENDPOINT_URL} \ -H 'Content-Type: application/json' \ -d '{"data":{"ndarray":[[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32941176470588235, 0.7254901960784313, 0.6235294117647059, 0.592156862745098, 0.23529411764705882, 0.1411764705882353, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.8705882352941177, 0.996078431372549, 0.996078431372549, 0.996078431372549, 0.996078431372549, 0.9450980392156862, 0.7764705882352941, 0.7764705882352941, 0.7764705882352941, 0.7764705882352941, 0.7764705882352941, 0.7764705882352941, 0.7764705882352941, 0.7764705882352941, 0.6666666666666666, 0.20392156862745098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2627450980392157, 0.4470588235294118, 0.2823529411764706, 0.4470588235294118, 0.6392156862745098, 0.8901960784313725, 0.996078431372549, 0.8823529411764706, 0.996078431372549, 0.996078431372549, 0.996078431372549, 0.9803921568627451, 0.8980392156862745, 0.996078431372549, 0.996078431372549, 0.5490196078431373, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.06666666666666667, 0.25882352941176473, 0.054901960784313725, 0.2627450980392157, 0.2627450980392157, 0.2627450980392157, 0.23137254901960785, 0.08235294117647059, 0.9254901960784314, 0.996078431372549, 0.41568627450980394, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.3254901960784314, 0.9921568627450981, 0.8196078431372549, 0.07058823529411765, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08627450980392157, 0.9137254901960784, 1.0, 0.3254901960784314, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5058823529411764, 0.996078431372549, 0.9333333333333333, 0.17254901960784313, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.23137254901960785, 0.9764705882352941, 0.996078431372549, 0.24313725490196078, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5215686274509804, 0.996078431372549, 0.7333333333333333, 0.0196078431372549, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.03529411764705882, 0.803921568627451, 0.9725490196078431, 0.22745098039215686, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.49411764705882355, 0.996078431372549, 0.7137254901960784, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.29411764705882354, 0.984313725490196, 0.9411764705882353, 0.2235294117647059, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.07450980392156863, 0.8666666666666667, 0.996078431372549, 0.6509803921568628, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.011764705882352941, 0.796078431372549, 0.996078431372549, 0.8588235294117647, 0.13725490196078433, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.14901960784313725, 0.996078431372549, 0.996078431372549, 0.30196078431372547, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.12156862745098039, 0.8784313725490196, 0.996078431372549, 0.45098039215686275, 0.00392156862745098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5215686274509804, 0.996078431372549, 0.996078431372549, 0.20392156862745098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.23921568627450981, 0.9490196078431372, 0.996078431372549, 0.996078431372549, 0.20392156862745098, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.4745098039215686, 0.996078431372549, 0.996078431372549, 0.8588235294117647, 0.1568627450980392, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.4745098039215686, 0.996078431372549, 0.8117647058823529, 0.07058823529411765, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]]}}'
E.g. response data; our service responds the inference that the number is 7 possibly due to the highest probability is at index-7.
{"data":{"names":[],"ndarray":[[2.2179587233495113e-07,1.2331390131237185e-08,2.5685869331937283e-05,0.0001267452462343499,3.6731301333858823e-10,8.802298339105619e-07,1.7313735514723483e-11,0.9998445510864258,5.112421490593988e-07,1.4923105027264683e-06]]},"meta":{"requestPath":{"model":"infuseai/tensorflow2-prepackaged:v0.1.0"}}}
We have deployed a prepared model as a service like a charm. In a real project, we may have different URIs of trained model files, as long as those URIs are accessible to PrimeHub, we can deploy models breezily in this way.
Furthermore, we may consider to use different pre-package servers or even customize one for services. For details, see Reference.