Hacker News Reader

Wow I actually have a perfect use case for this in a hobby project. Great timing.

I considered the older version but it's very limited:

> The original Teachable Machine only let you train 3 classes, whereas now you can add as many classes as you like.

I'm curious to see how far this scales, for example can I have a few hundred thousand classes? If so, what are the consequences, if any?

View on HN

v1 used a very limited (albeit very easy and already quite impressive) form of transfer learning, e.g. take a pretrained network's 1000dim vector outputs given a bunch of images belonging to three sets (since the original was trained on Imagenet), and then just use K-NN to predict what a set "new" image falls into.

v2 does actually finetune weights of a pretrained network. At the time, it was a nice showcase how fast fast JS ML libraries were evolving.

Reply on news.ycombinator.com