In the previous two chapters, you learned how to use supervised ML algorithms (Chapter 3, Supervised Learning) and unsupervised ML algorithms (Chapter 4, Unsupervised Learning) to solve a wide range of problems. The solutions created models from scratch and consisted only of Go code. We did not use models that had already been trained, nor did we attempt to call Matlab, Python, or R code from Go. However, there are several situations in which this can be beneficial. In this chapter, we will present several strategies aimed at using pretrained models and creating polyglot ML applications – that is, where the main application logic is written in Go but where specialist techniques and models may have been written in other languages.
In this chapter, you will learn about the following topics:
- How to load a pretrained GoML model and use it to generate...