Teachable Machine

Teachable Machine Train a computer to recognize your own images, sounds, & poses. A fast, easy way to create machine learning models for your sites, apps, and more – no expertise or coding required. Get Started What is Teachable Machine? Teachable Machine is a web-based tool that makes creating machine learning models fast, easy, and accessible to everyone. (Note: you can find the first version of Teachable Machine from 2017 here.) How do I use it? 1 Gather Gather and group your examples into classes, or categories, that you want the computer to learn. Video: Gather samples 2 Train Train your model, then instantly test it out to see whether it can correctly classify new examples. Video: Train your model 3 Export Export your model for your projects: sites, apps, and more. You can download your model or host it online. Video: Export your model What can I use to teach it? Teachable Machine is flexible – use files or capture examples live. It’s respectful of the way you work. You can even choose to use it entirely on-device, without any webcam or microphone data leaving your computer. Images Teach a model to classify images using files or your webcam. Sounds Teach a model to classify audio by recording short sound samples. Poses Teach a model to classify body positions using files or striking poses in your webcam. Tutorials Images: Bananameter Learn how to create a model that can tell if a banana is ripe or not. Sound: Snap Clap Whistle Learn how to create a model that detects simple sounds you make. Pose: Head Tilt Learn how to create a model that recognizes which way you’re tilting your head. Made with Teachable Machine Tiny Sorter A DIY experiment connecting Arduino and Teachable Machine. Learn more Project Euphonia Steve Saling is using Teachable Machine to communicate in new ways, such as using facial gestures to trigger sounds. Watch video Teachable Snake Vince MingPu Shao used Teachable Machine to turn their webcam and a piece of paper into a game controller. Learn more Teachable Sorter A physical machine that you can teach to rapidly recognize and sort objects using your own custom machine learning models. Learn more Teachable Arcade Use Teachable Machine to train a video game controller. (Also see the accompanying lesson plan below.) Learn more Check out more experiments made with Teachable Machine here. If you've made something you want to share with us, just email teachablemachine-support@google.com. Works with… The models you make with Teachable Machine are real TensorFlow.js models that work anywhere javascript runs, so they play nice with tools like Glitch, P5.js, Node.js & more. Plus, export to different formats to use your models elsewhere, like Coral, Arduino & more. FAQ: Saving & Exporting For Learning Want to learn using Teachable Machine? Here are some lessons & activities folks have made with it: AI + Ethics by Blakeley H. Payne, Personal Robots Group, MIT Media Lab A lesson for students to start understanding bias in algorithmic systems. Common Core, K-8, tech Dancing with AI by MIT Media Lab Use Teachable Machine and PoseBlocks to create interactive systems. K-8, tech Ready AI Lesson by Ready AI Explore Teachable Machine and learn the concepts of machine learning, classification, and societal impact. K-12 Tweets @pushmatrix Google's Teachable Machine is a magical ML tool. ✨ In 2 minutes I trained my computer to recognize what part of my shoe it was looking at. You have to try it: https://teachablemachine.withgoogle.com @thecodingtrain we've been in zoom land for how long now? 😭 we just released a new video showing you how to augment your video calls using @p5xjs @ml5js Teachable Machine + OBS. ty for the idea @cameronhunter 🌟 🎥 https://youtu.be/9z9mbiOZqSs 💻 https://thecodingtrain.com/CodingChallenges/157-zoom-annotations.html @blakeleyhpayne “Kids are given images of both and use Google’s Teachable Machines to train the data.” It was a joy to collaborate with @WarronBebster, @ire_alva, @alexanderchen, and @hapticdata and have them in our classroom. You can check out the tool here: teachablemachine.withgoogle.com @yining_shi Teachable Machine is so helpful to people who have creative ideas and beginners to machine learning or programming! Here are some very cool projects students made with Teachable Machine + @p5xjs in Machine Learning for the Web class at @ITP_NYU: https://github.com/yining1023/teachable-machine-p5 @jetscott Teachable Machine: a project training sound recognition to win a tractor race! By Steve Saling, who created it to explore how to train for non standard speech interactions for ALS, stroke and others who need assistance #io19 @anildash Really extraordinary set of tools from Google Creative Lab, including this @Glitch app that’s a starter for Teachable Machine — letting you train your own machine learning projects right in a web browser. This is what helped me finally understand this stuff! See what people are making: #teachablemachine on Twitter Looking for the first version from 2017? Open site More questions? Check our FAQ. --- New Project Teach based on images, from files or your webcam. Teach based on one-second-long sounds, from files or your microphone. Teach based on images, from files or your webcam. More coming soon More models will appear here as they’re developed. release-2-4-12 - 2.4.12#5704f5 --- teachablemachine.withgoogle.com uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn moreUnderstood Teachable Machine Teach a machine using your camera, live in the browser. No coding required. Let’s Go! or skip the tutorial Something went wrong and we could not load the site, please try restarting your browser. Mobile version is highly experimental. If you’re new to machine learning, visit the site on a desktop for a helpful first-time tutorial and better performance. GOT IT Sorry, looks like your browser or device doesn't support this experiment. Learn more about Teachable Machine here. Or try visiting this site on a desktop computer in a browser like Chrome. Privacy & Terms Input Learning 0 examples Reset Confidence 0% Train Green 0 examples Reset Confidence 0% Train Purple 0 examples Reset Confidence 0% Train Orange Output GIF Sound Speech Load more Skip Tutorial Record a 10-second video clip. You can use your mic to say something about it. Download your video below, or redo it. 0:10 Start Recording Download it! (Heads up, sharing doesn't work just yet. It should be be working soon!) By checking this box I certify that I am over 13 years old Record a video Share your machine with a screen captured video. What is this? This experiment lets anyone explore how machine learning works, in a fun, hands-on way. You can teach a machine to using your camera, live in the browser – no coding required. You train a neural network locally on your device, without sending any images to a server. That’s how it responds so quickly to you. Watch this video to learn more: What kind of things can I do? Here are some links to things people have done so far: Make your hand say moo. Rock out by wiggling your fingers. And stay tuned, we’ll add more examples here soon. (Want to share something with us? Use the record button and share it on social media with #teachablemachine so we can check it out.) Any tips I should keep in mind? Capture at least 30 images per class. Be aware of when you’re pressing and releasing the button (that’s when it starts/stops capturing images). And you might need to capture lots of angles or variations of whatever it is you want your machine to recognize. Why isn’t my machine working the way I want it to? Don’t worry. Keep playing around. Seeing what works and what doesn’t is one way to explore how machine learning works. Keep in mind that your machine doesn’t have an understanding of higher level concepts, like faces or objects. It’s learning through the examples you give it. So if it’s not working the way you want, you might want to click the x to reset your classes and try out different approaches. Where can I find more things like this? Check out Wekinator by Rebecca Fiebrink, one of the inspirations for this project. It lets anyone use machine learning through simple actions instead of code. Here are some interactive guides for learning about machine learning. And check out other fun projects like this and this. Are my images being stored on Google servers? No. All the training is happening locally on your device. How do I learn more about machine learning? Here’s an intro-level video explainer. This site lets you interact with neural networks in more detail. And this free online course lets you dive in even deeper. How was this built? The image classification is powered by a neural network. It was made possible by Nikhil Thorat and Daniel Smilkov, the team behind TensorFlow.js. It’s an open-source library that allows web developers to train and run machine learning models locally in the browser. The code for this experiment is open-sourced here on Github. We also made a boilerplate project which demonstrates how to use TensorFlow.js to create projects of your own like Teachable Machine here. Who made this? This experiment was a collaborative effort by friends from Støj, Use All Five and Creative Lab and PAIR teams at Google. To teach your machine, you need to click up here to turn on your camera and then refresh the page. you need to refresh the page and allow camera access. --- New Project Teach based on images, from files or your webcam. Teach based on one-second-long sounds, from files or your microphone. Teach based on images, from files or your webcam. More coming soon More models will appear here as they’re developed. release-2-4-12 - 2.4.12#5704f5