Testing NeuNetS model deployments

You can deploy your NeuNetS model to your IBM Watson Machine Learning service from the NeuNetS tool. This topic describes how to test a model you have built in NeuNetS and then deployed to your IBM Watson Machine Learning service. NeuNetS is currently in beta.

 

Deployment details page

After you have deployed your NeuNetS model to your Watson Machine Learning service, a message appears in the NeuNetS tool with a link to the deployment details page.

You can navigate to your deployment details page from your project at any time:

  1. From your project in Watson Studio, click the Deployments tab
  2. Click on the name of the deployment to open the deployment details page

 

Testing deployments

You can test your model deployment in the Test tab of the deployment details page by entering valid JSON-formated payload data into the input data box.

See: NeuNetS model deployments payload format.

 

Example 1: Testing a text classifier

If you created the UCI: SMS Spam Collection sample model in NueNetS, here are sample test payloads you can use to test the model:

  • Class: “ham”
    { "values" : [ "Going for dinner.msg you after." ] }
    
  • Class: “spam”
    { "values" : [ "URGENT! We are trying to contact you. You have won a £900 prize GUARANTEED." ] }
    

To test the model, paste a sample payload into the text box in the deployment Test tab and then click Predict:

Testing the CIFAR-10 sample model

 

Example 2: Testing an image classifier

If you created the CIFAR-10 sample model in NueNetS, here are sample test payloads you can use to test the model:

To test the model, copy the payload from one of those sample files into the text box in the deployment Test tab and then click Predict:

Testing the CIFAR-10 sample model