The value-add for this demo is amazing, it's going to be many people's first approachable experience of ml, or things just like this will be. I expect a lot more of this stuff to appear in UI/UX. It's fun, intuitive, and a game changer away from dumb screens to fully interactive machines with their own knowledge graph.
Teachable Machine: Teach a machine using your camera, live in the browser
71–80 of 95 posts
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#72Earlier quoted context omitted.
We're using SqueezeNet ( https://github.com/DeepScale/SqueezeNet ), which is similar to Inception (trained on the same ImageNet dataset) but is much smaller - 5MB instead of inception's 100MB - and inference is much much quicker. The application takes webcam frames and infers through SqueezeNet, producing a 1000D logits vector for each frame. These can be thought of as unnormalized probabilities for each of ImageNet'…
Interesting! I'm curious why you've used a different classification algorithm on top of a neural network. I would expect that a neural network on top of a pretrained network could give similar results, with the benefit of simpler code. Is performance the reason? Anyway, I'm looking forward to your blog post.
Basically, read this paper: https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#73Earlier quoted context omitted.
Surprisingly well! It's a really well put together demo & tutorial. I held a pen up next to me and held the green button. Then did the same with a mouse. It would flick between the two if I was holding nothing, so I held the orange button for a bit while holding nothing. Worked pretty much every time. Training is fast enough with a few hundred images per class that I didn't notice any delay.
What do you mean exactly by "held the green button"? I can't run the demo here (browser not capable enough, and no camera) and I'm getting really curious what this is about.
Ah sorry. So there are three coloured buttons. When you hold one, the site takes a series of photos from your webcam, and assign them to that "class". Then it'll train and start classifying your video input live.
It's a pretty neat way of creating a reasonable training set of 3 classes.
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#74Am I the only paranoid one who thinks this is just Google's way of capturing millions of faces in their database? Or did Apple beat them to it?
You're paranoid because if google wants a million faces, they can get then any number of less conspiracy laden ways.
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#75The paranoia in this thread is crazy. It's client side, people, and if google wanted to steal your precious fluids, they wouldn't need this to do it.
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#76What makes it non-mobile? Is it something about the expected performance of the JS? or are there apis being used im not thinking about?
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#77What makes it non-mobile? Is it something about the expected performance of the JS? or are there apis being used im not thinking about?
It works on mobile, it's just slow. Every time we read and write from memory we have to pack and unpack 32 bit floats as 4 bytes without bit shifting operators >.>
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#78i bet it's fine tuning an ImageNet CNN
kinda, ya
Re: Teachable Machine: Teach a machine using your camera, live in the browser
#79Earlier quoted context omitted.
Training a neural network on top would require a "proper" training phase, and finding the right hyperparameters that work everywhere turned out to be tricky. Actually, this is what we did originally, in the blog post we'll try to show demos of each of the approaches and explain why they don't work. KNN also makes training "instant", and the code much much simpler.
That makes sense. By the way, I think your software could become very popular on the Raspberry Pi, because it would be very cheap and fun to use it for all sorts of applications (e.g. home automation).