May 5, 2022 · Coral is a complete toolkit to build products with local AI. Our on-device inferencing capabilities allow you to build products that are efficient, private, fast and offline.

Mendel Linux To ease development with our fully-integrated systems (the Dev Board, Dev Board Mini, and System-on-Module), we created an open-source derivative of Debian Linux called Mendel.. We've optimized Mendel for embedded systems by making it very lightweight.

Helping you bring local AI to applications from prototype to production For prototyping Our prototyping products make it easy to take your idea from sketch into proof-of-concept.

Product lifecycle. Product line enhancements and upgrades may bring products such as this one to the end of their life cycle. Once an End-Of-Life (EOL) notice is posted online, you can continue to purchase the product until the Last Time Buy Date, assuming that it is still available.Our goal is to assist you in making your final purchases of the product subject to …

An open source AI experiment that introduces the basics of machine learning by helping you build a teachable object using a Raspberry Pi Zero and the Coral USB Accelerator.

Product lifecycle. Product line enhancements and upgrades may bring products such as this one to the end of their life cycle. Once an End-Of-Life (EOL) notice is posted online, you can continue to purchase the product until the Last Time Buy Date, assuming that it is still available.Our goal is to assist you in making your final purchases of the product subject to …

Coral helps you bring on-device AI application ideas from prototype to production. We offer a platform of hardware components, software tools, and pre-compiled models for building devices with local AI.

Next steps. To run some other models, such as real-time object detection, pose estimation, keyphrase detection, on-device transfer learning, and others, check out our example projects.In particular, if you want to try running a model with camera input (including support for the Raspberry Pi camera), try one of the several camera examples.. If you want to train your own model, try these tutorials:

Note: If you pass a model to the Edge TPU Compiler that uses float inputs, the compiler leaves a quantize op at the beginning of your graph (which runs on the CPU). So as long as your tensor parameters are quantized, it's okay if the input and output tensors are float because they'll be converted on the CPU.

Microphone. The Dev Board Micro includes one on-board pulse-density modulation (PDM) microphone. To use the microphone with Arduino, you need to use the global instance of the global instance of the PDMClass object called Mic.. This API is designed to be code-compatible with projects that use the Arduino PDM library, but it …