crafting (and) JavaScript

August 2020

I renamed the series to "ML for VRT" instead of "ML vs. VRT" since that is what I actually want to achieve (eventually), as you can read in Part 1 - Machine Learning vs. Screenshot Comparing?. Read on to figure out how I ended up next to learn about neural networks, because I figured out just applying some code examples learned from tutorials won't suffice my learning and they won't answer the questions I actually have to understand how to tune a neural network to do what I image it to do, detecting screenshots for visual regression testing.

In part 1 I started my naive investigation on how to apply machine learning for making visual regression tests (VRT) better. I described the problem to solve, explored Keras very superficially and did also touched on the complexity of doing ML myself as opposed to having colleagues who are experts and who throw phrases like "train a model" and "predict" etc. around.
Oh boy, did I underestimate this.