Evaluate Models

After you train your model, PerceptiLabs can evaluate its performance on the testing part of your data that you allocated in the training settings when you created the model.

Running a Test

Follow the steps below to run a test:

1) Click Go to Test when PerceptiLabs displays the Result popup after training completes:

Alternatively, you can access the Evaluate View screen directly using Evaluate Tab on the left, and then start a test for a model that has completed training:

2) Click New Test on the Evaluate View screen:

3) Populate the options in the Test Configuration popup:

• Test dataset: set to Use Partitioned Dataset.

• Selected model(s): dropdown allowing you to select the trained model(s) to test.

• Select tests: allows you to select one or more tests to perform. The tests available depend on the type of Component(s) in the selected model(s). See Types of Tests for more information.

4) Click Run Test after you have completed the configuration, to start running the configured test(s). The test results will be displayed when the test completes:

Example of test results, in this case, a classification matrix.

Congratulations, you've now built, trained, and evaluated your model. When you're happy with your model's performance, read Export and Deploy Models to learn how to use your model for real-world inference.