face-api.js

The facial exam (emotions) was quite interesting, although not very accurate, I had to spend over 1 minute on some of the emotions. At least it's powered by a very tiny ML model that runs locally in the browser, powered by https://github.com/justadudewhohacks/face-api.js > The face expression recognition model is lightweight, fast and provides reasonable accuracy. The model has a size of roughly 310kb and it employs depthwise separable convolutions and densely connected blocks. It has been trained on a variety of images from publicly available datasets as well as images scraped from the web. Note, that wearing glasses might decrease the accuracy of the prediction results.

For those looking to not only detect, but also vectorize faces (for later comparison against other faces) -- face recognition, try out: face-api.js https://github.com/justadudewhohacks/face-api.js/

For the record - the author considered these two libraries for face detection: https://github.com/vladmandic/human & https://github.com/justadudewhohacks/face-api.js, he chose "vladmandic/human".

You make reference to a "weights" folder, but I'm not seeing it in the repo - am I looking in the wrong place? EDIT: My mistake, you said it was in the library repo and there it was. For anyone who needs it - https://github.com/justadudewhohacks/face-api.js

A lot of the good stuff seems to be coming from: https://github.com/justadudewhohacks/face-api.js Results are poor, as expected. I think the author intends it as a joke. But the message is spot on.