A browser-based tool that lets anyone create machine learning models without writing code, using TensorFlow.js.
Teachable Machine is a web-based tool that allows users to create and train custom machine learning models directly in their browser without writing any code. It enables people to build models that can recognize images, sounds, or poses by simply providing examples through their webcam, microphone, or uploaded files. The tool uses TensorFlow.js to run everything locally in the browser, making machine learning accessible to non-programmers.
Educators, artists, designers, students, and beginners who want to explore machine learning concepts without programming experience. It's also useful for developers looking for a quick way to prototype ML models before implementing them in code.
It provides the simplest possible entry point to machine learning with instant visual feedback and no setup required. Unlike traditional ML tools that require coding and complex environments, Teachable Machine works entirely in the browser with an intuitive interface that makes advanced technology accessible to everyone.
Explore how machine learning works, live in the browser. No coding required.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
The intuitive drag-and-drop interface eliminates programming needs, making ML accessible to educators, artists, and beginners for hands-on experimentation.
All processing occurs locally in the browser using TensorFlow.js, ensuring user data never leaves their device and no server dependency.
Supports image classification, audio recognition, and pose detection models, enabling a wide range of creative and educational applications.
Trained models can be exported as TensorFlow.js or TensorFlow Lite files, allowing quick integration into other projects or apps for rapid testing.
Users cannot adjust training parameters, model architectures, or use advanced techniques like transfer learning, restricting flexibility for specialized needs.
Local development requires HTTPS configuration, dependency management with yarn, and key generation, which contradicts the no-code simplicity for developers.
Training is confined to browser capabilities, making it slow or impractical for large datasets, complex models, or real-time performance on low-end devices.