coral-pi-rest-server

Perform inferencing of tensorflow-lite models on an RPi with acceleration from Coral USB stick

MIT License

Stars

67

View Code on GitHub Visit Website View on X

Ecosystems: Python, Raspberry Pi, Tensorflow

Bot releases are visible (Hide)

coral-pi-rest-server - Allow you to pass a min_confidence Latest Release

Published by robmarkcole almost 2 years ago

Allow you to pass a min_confidence in the form post similar to how deepstack operates.

coral-pi-rest-server - Bugfix

Published by robmarkcole over 2 years ago

fixes https://github.com/robmarkcole/coral-pi-rest-server/issues/62

coral-pi-rest-server - Update to use pycoral

Published by robmarkcole about 3 years ago

Update to use pycoral library

coral-pi-rest-server - Kinda stable so release

Published by robmarkcole over 4 years ago

coral-pi-rest-server - Adds basic logging and service

Published by robmarkcole about 5 years ago

Adds basic logging to file and adds a service for running the app on restart of the pi

coral-pi-rest-server - Use args

Published by robmarkcole about 5 years ago

Use args to allow setting:

Port
Model directory
Model file
Labels file

coral-pi-rest-server - Use disk images from edgetpu-platforms

Published by robmarkcole about 5 years ago

Use disk images from edgetpu-platforms to simplify setup for raspberry pi users

coral-pi-rest-server - Fix confidence as float

Published by robmarkcole about 5 years ago

Fixes an inconsistency with deepstack

coral-pi-rest-server - Makes deepstack compatible

Published by robmarkcole about 5 years ago

Returns data in same format as https://python.deepstack.cc/object-detection for use with https://github.com/robmarkcole/HASS-Deepstack-object

coral-pi-rest-server - Adds Docker support

Published by robmarkcole over 5 years ago

Adds Docker file, big thanks to @lmamakos

coral-pi-rest-server - Fixes bounding boxes

Published by robmarkcole over 5 years ago

As title, see the jupyter notebook for example

coral-pi-rest-server - Returns confidence

Published by robmarkcole over 5 years ago

Returns a confidence in % (percentage)

coral-pi-rest-server - Basic functionality

Published by robmarkcole over 5 years ago

Basic functionality of loading the object detection model, and exposing predictions via Flask app

Related Projects

DeepCamera

Open-Source AI Camera. Empower any camera/CCTV with state-of-the-art AI, including facial recogni...

05 Mar 2019 1,823

tensorflow-lite-rest-server

Expose tensorflow-lite models via a rest API using FastAPI

RPi-image

Raspberry Pi 4 Buster 64-bit OS with deep learning examples

15 Mar 2021 133

MobileNet-SSDLite-RealSense-TF

RaspberryPi3(Raspbian Stretch) + MobileNetv2-SSDLite(Tensorflow/MobileNetv2SSDLite) + RealSense D...

benchmarks

TensorFlow, TensorFlow-Lite Pytorch, Torchvision, TensorRT Benchmarks