is there inference example to verify federated-learning models?

[xinzongyan]

I completed the federated-learning-surface-defect-detection example with image kubeedge/sedna-example-federated-learning-surface-defect-detection-train:v0.4.0

Both edge nodes generate the following Model file in the output directory：

saved_model.pb the files in variables directory: variables.data-00000-of-00001 variables.index

I want to know how to use these models and whether there are inference worker examples to verify whether these models are correct.