with contributions from Yannick Assogba, Ping Yu and Nick Kreeger

12.1  Testing TensorFlow.js Models

12.1.1  Traditional unit testing

12.1.2  Testing with golden values

12.1.3  Considerations around continuous training

12.2  Model Optimization

12.2.1  Model-size optimization through post-training weight quantization

12.2.2  Inference speed optimization using GraphModel conversion

12.3  Deploying TensorFlow.js models on various platforms and environments

12.3.1  Additional considerations when deploying to the web

12.3.2 Deployment to cloud serving

12.3.3 Deploying to a browser extension, like Chrome Extension

12.3.4  Deploying TensorFlow.js models in JavaScript-based mobile applications

12.3.5  Deploying TensorFlow.js models in JavaScript-based cross-platform desktop applications

12.3.6 Deploying TensorFlow.js models on WeChat and as other JavaScript-based mobile app plugin systems

12.3.7. Deploying TensorFlow.js models on single-board computers

12.3.8 Summary of deployments

12.4  Summary

12.5  Materials for further reading

12.6  Exercises