Coral - Build beneficial and privacy preserving AI 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
Accelerator Module - Coral 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 EOL and to help you smoothly transition to new products
Dev Board Mini - Coral 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 EOL and to help you smoothly transition to new products
Camera - Coral 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 EOL and to help you smoothly transition to new products
Models - All | Coral (All models are compatible with all other Coral boards ) * Although Dev Board Micro supports all the PoseNet MobileNet V1 models, beware that the on-board camera is 324x324 px, so you should use only the 324x324x3 model, unless you connect a larger-resolution camera
M. 2 Accelerator 2x Edge TPU (Dakota) datasheet - Coral Description The Coral M 2 Accelerator with Dual Edge TPU is an M 2 module (E-key) that includes two Edge TPU ML accelerators, each with their own PCIe Gen2 x1 interface
De v Board Dat asheet - Coral If you are interested in using the Coral SoM with custom PCB hardware (instead of the baseboard provided with the Dev Board), you can learn more about the standalone SoM in the Coral SoM datasheet
Models - Object Detection | Coral With the Coral Edge TPU™, you can run an object detection model directly on your device, using real-time video, at over 100 frames per second You can even run multiple detection models concurrently on one Edge TPU, while maintaining a high frame rate
libcoral API overview | Coral The Coral C++ API (libcoral) is built atop the TensorFlow Lite C++ API to simplify your code when running an inference on the Edge TPU, and to provide advanced features for the Edge TPU such as model pipelining across multiple Edge TPUs, and on-device transfer learning
Models - Semantic segmentation | Coral With the Coral Edge TPU™, you can run a semantic segmentation model directly on your device, using real-time video, at over 100 frames per second You can even run a second model concurrently on one Edge TPU, while maintaining a high frame rate