edgetpu

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

custom human activity recognition modules by pose estimation and cascaded inference using sklearn API

Self-hosted NVR with object detection

Coral issue tracker (and legacy Edge TPU API source)

Deep Learning Autonomous Car based on Raspberry Pi, SunFounder PiCar-V Kit, TensorFlow, and Google's EdgeTPU Co-Processor

This script converts the ONNX/OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC/NCHW) -> TFLite (NHWC/NCHW). And the conversion from .pb to saved_model and from saved_model to .pb and from .pb to .tflite and saved_model to .tflite and saved_model to onnx. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support.

YOLOv4 Implemented in Tensorflow 2.

Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite, ONNX, OpenVINO, Myriad Inference Engine blob and .pb from .tflite. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support. Supports inverse quantization of INT8 quantization model.

Sample projects for TensorFlow Lite in C++ with delegates such as GPU, EdgeTPU, XNNPACK, NNAPI

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

Motion transfer booth for a 1 hour everybody dance now video generation using EdgeTPU and Tensorflow 2.0

Docker with Raspbian, SSH and the Coral USB Edge TPU libraries.

ROS package for Coral Edge TPU USB Accelerator

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

Multiple types of NN model optimization environments. It is possible to directly access the host PC GUI and the camera to verify the operation. Intel iHD GPU (iGPU) support. NVIDIA GPU (dGPU) support.

This project contains a set of scripts to facilitate the setup of the Jetson Nano for doing Deep Learning with Tensorflow 2.0 (and also with Coral TPU Edge)

The products,docs,resources,software,tools,scripts,models,demos

Experimental Kubernetes Device Plugin for Coral Edge TPU

Raspberry Pi Supplement to Coral Edge TPU Demo

some scripts I used to test Google's Edge TPU

BiSeNet V2 TensorFlow 2 Implementation capable of running on Edge TPUs

edgetpu-native from https://coral.googlesource.com/edgetpu-native

Just a simple Flask web app for Coral Edge TPU. For streaming and testing your object detection/classification models.

Google cloud edge TPU edgetpuvision research/learning repo

A real world application of pytorch, transfer learning and edge TPU to detect when my dog uses the restroom.

Drive a RC car on a track, detecting lanes using semantic segmentation. Uses Donkeycar, ROS, Raspberry Pi 4, Google Edge TPU.

Docker container for Google EdgeTPU compiler

A simple python api for Google Edge TPU online compiler.

Final Year Project - Traffic Sign Detection on a custom Raspberry Pi RC car. Manual and Autonomous.