GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → leehaesung → TensorFlow-Powered_Robot_Vision

leehaesung / TensorFlow-Powered_Robot_Vision

Licence: other
No description or website provided.

Programming Languages

Jupyter Notebook
11667 projects

Labels

recognitionjupyter-notebookinceptiontensorflow-image-classifier

Projects that are alternatives of or similar to TensorFlow-Powered Robot Vision

Epic Kitchens 55 Action Models
EPIC-KITCHENS-55 baselines for Action Recognition
Stars: ✭ 68 (+100%)
Mutual labels:  recognition, inception
iOS-CoreML-Inceptionv3
Real-time Object Recognition using Apple's CoreML 2.0 and Vision API -
Stars: ✭ 46 (+35.29%)
Mutual labels:  recognition, inception
facial-expression-recognition
The main purpose of the project - recognition of emotions based on facial expressions. Cohn-Kanade data set (http://www.pitt.edu/~emotion/ck-spread.htm) is used for explorations and training
Stars: ✭ 60 (+76.47%)
Mutual labels:  recognition
DecisionAmbiguityRecognition
Deep learning AI, that recognizes when are people uncertain
Stars: ✭ 16 (-52.94%)
Mutual labels:  recognition
SkeletonMatching
This repository implements skeleton matching algorithm.
Stars: ✭ 30 (-11.76%)
Mutual labels:  recognition
Classify-Real-Time-Desktop
Inception model used to classify camera feed on real time. Coded during the Deep Learning Hackathon 2017 San Francisco
Stars: ✭ 44 (+29.41%)
Mutual labels:  inception
Korean-OCR-Model-Design-based-on-Keras-CNN
Korean OCR Model Design(한글 OCR 모델 설계)
Stars: ✭ 34 (+0%)
Mutual labels:  recognition
Awesome-Human-Activity-Recognition
An up-to-date & curated list of Awesome IMU-based Human Activity Recognition(Ubiquitous Computing) papers, methods & resources. Please note that most of the collections of researches are mainly based on IMU data.
Stars: ✭ 72 (+111.76%)
Mutual labels:  recognition
tensorflow-image-classifier
Easily train an image classifier and then use it to label/tag other images
Stars: ✭ 29 (-14.71%)
Mutual labels:  tensorflow-image-classifier
timeline
Timeline - A photo organizer
Stars: ✭ 39 (+14.71%)
Mutual labels:  recognition
rutimeparser
Recognize date and time in russian text and return datetime.datetime.
Stars: ✭ 17 (-50%)
Mutual labels:  recognition
img classification deep learning
No description or website provided.
Stars: ✭ 19 (-44.12%)
Mutual labels:  inception
SRLCD
fast loop closure detection (online visual place recognition) via saliency re-identification IROS 2020
Stars: ✭ 78 (+129.41%)
Mutual labels:  recognition
small model face recognition
针对移动端的人脸识别需求，训练测试一些相关的小模型实验。
Stars: ✭ 27 (-20.59%)
Mutual labels:  recognition
Identifying-Clothing-Attributes
Pretrained VGG-16 network as feature extractor for Object Recognition (Python, Keras, Scikit-Learn)
Stars: ✭ 22 (-35.29%)
Mutual labels:  recognition
Hand-Digits-Recognition
Recognize your own handwritten digits with Tensorflow, embedded in a PyQT5 GUI. The Neural Network was trained on MNIST.
Stars: ✭ 11 (-67.65%)
Mutual labels:  recognition
VideoRecognitionTracking
Real time object or face detection recognition and tracking in video. The Full end-to-end project.
Stars: ✭ 36 (+5.88%)
Mutual labels:  recognition
Nearest-Celebrity-Face
Tensorflow Implementation of FaceNet: A Unified Embedding for Face Recognition and Clustering to find the celebrity whose face matches the closest to yours.
Stars: ✭ 30 (-11.76%)
Mutual labels:  inception
openface mass compare
An openface script that runs a REST server. Posted images are compared against a large dataset, and the most likely match is returned. Works with https://hub.docker.com/r/uoacer/openface-mass-compare/
Stars: ✭ 22 (-35.29%)
Mutual labels:  recognition
etiketai
Etiketai is an online tool designed to label images, useful for training AI models
Stars: ✭ 63 (+85.29%)
Mutual labels:  recognition
View All Similar Projects ➔

TensorFlow-Powered Vision For Pi-based robot

Introduction

This is a Pi-based robot to implement visual recognition(Inception V3). The TensorFlow-Powered vision can recognize many objects such as people, car, bus, fruits, and so on.

  • Hardware: Raspberry-Pi2, Sony PS3 Eye Camera

    (Available to use Logitech C270 USB camera with Raspberry Pi)

  • Software: TensorFlow(v1.0.1), Jupyter-Notebook

  • Schematics: Only USB Camera Part

Structure.png

My motivation

I was so curious about excellence of the image recognition with TensorFlow on Raspberry Pi. Also, the Jupyter notebook is very convenient to instantly code as a quick prototype. So, in terms of error rate of the image classification, Inception V3(3.46%) is more excellent than human(5.1%) whereas raspberry pi's processing speed is very slow compare to my laptop.

(Table: Jeff Dean's Keynote @Google Brain).

Chart_IR.png

  • Schematic diagram of Inception-v3

InceptionV3.png

Requirements and Installation

  • Install a webcam driver on your Rapsberry Pi.
sudo apt-get install fswebcam
  • Test your webcam.
fswebcam test.jpg

Quick Start

  • You should install both TensorFlow(v1.0.1) and Jupyter notebook on your Raspberry Pi.

  • First, clone the TensorFlow-Powered_Robot_Vision git repository here. This can be accomplished by:

cd /home/pi/Documents
git clone https://github.com/leehaesung/TensorFlow-Powered_Robot_Vision.git

next, cd into the newly created directory:

cd TensorFlow-Powered_Robot_Vision

Drive your jupyter notebook on your Raspberry Pi.

jupyter-notebook

The pre-trained data(inception_v3.ckpt) will automatically download when driving the Jupyter notebook. (Where: /pi/home/Documents/datasets/inception)

Source Codes

Results of Object Recognition

  • Wow! The result is really awessome!!

RecognitionResult.png

How To Retrain

References

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].