Python API for ML inferencing and transfer-learning on Coral devices

Dual Edge TPU Adapter to use it on a system with single PCIe port on m.2 A/B/E/M slot

Neuralet is an open-source platform for edge deep learning models on edge TPU, Jetson Nano, and more.

Fast object detection, face recognition and S3 upload of ZoneMinder alarms.

A workout trainer Dash/Flask app that helps track your HIIT workouts by analyzing real-time video streaming from your sweet Pi using machine learning and Edge TPU..

Social Distancing Detector using deep learning and capable to run on edge AI devices such as NVIDIA Jetson, Google Coral, and more.

The easiest way to count pedestrians, cyclists, and vehicles on edge computing devices or live video feeds.

TensorFlow Lite, Coral Edge TPU samples (Python/C++, Raspberry Pi/Windows/Linux).

Run Tiny YOLO-v3 on Google's Edge TPU USB Accelerator.

Advanced driver-assistance system with Google Coral Edge TPU Dev Board / USB Accelerator, Intel Movidius NCS (neural compute stick), Myriad 2/X VPU, Gyrfalcon 2801 Neural Accelerator, NVIDIA Jetson Nano and Khadas VIM3

ROS package for the Google Edge TPU

Quantized Tensorflow Estimator for Google EdgeTpu Accelerator, Dev Board and Intel Neural Compute Stick 2

Coral Edge TPU compilable version of DeepLab V3

m.2 B+M Coral TPU card for Raspberry Pi CM4

Examples for playing with the coral edge TPU

Pure-Python Edge TPU driver for custom computation beyond ML inference

Edge deployable spatio-temporal violence detector using transformers

A simple and real-time traffic monitoring solution using TensorFlow and OpenCV.

High FPS live stream Raspberry Pi cam with object detection by Google Coral EdgeTPU

ThinkBioT is an Bioacoustic sensor framework for the collection, processing and satellite transmission of Bio-Taxa Classification and Acoustic Indices data.

Person Detection with Raspberry Pi and Coral Edge-TPU for my master thesis

Detect herons and trigger an alarm

Fixing TFLite INT8 quantization for small objects in satellite imagery. A drop-in wrapper for focus-based calibration.

Pipeline for mask detection over a Pi camera video feed.

A multi-use helmet that tells you what is behind you using machine learning. This is a continuation of the TPU bike project.

Coral m.2 TPU on raspberry pi 5

Prebuilt binary for EdgeTPU PythonAPI standalone installer.

Integrate your rtsp cameras with simple person detection into a Home Assistant device with MQTT

Train, Quantize and Export a YOLO model for the Coral USB Accelerator.

Google Coral Edge TPU libraries compiled for legacy CPUs (SSSE3 only, no SSE4.2/AVX). Enables Coral PCIe TPU on Intel Atom and other pre-2013 CPUs with Frigate NVR.