Smile App

Smile App mimics a person's emotions, age, and gender from CAM, Video, and Picture and sends data to the MQTT broker. In the frontend, Smile is changing real-time.

App

Project Set Up and Installation

Requirements

Hardware

• 6th to 10th generation Intel® Core™ processor with Iris® Pro graphics or Intel® HD Graphics.
• VPU - Intel® Neural Compute Stick 2 (NCS2)
• FPGA

Software

• Intel® Distribution of OpenVINO™ toolkit 2019 R3 release docs
• Intel DevCloud

Model installations

• Face Detection Model
• Age Gender Recognition
• Emotion Recognition Model

Installation commands

Face Detection Model

python "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\tools\model_downloader\downloader.py" --name "face-detection-adas-binary-0001" -o "your directory"\models 

Age Gender Recognition

python "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\tools\model_downloader\downloader.py" --name "age-gender-recognition-retail-0013" -o "your directory"\models 

Emotion Recognition Model

python "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\tools\model_downloader\downloader.py" --name "face-detection-adas-binary-0001" -o "your directory"\models

Configuration for Python files

Activate virtualenv

• virtualenv appenv
• appenv\Scripts\activate In the directory run: pip install -r requirments.txt

Running the App

From the main directory:

Start the Mosca Server

cd webservice/server/node-server
npm install
node ./server.js

You should see the following message, if successful: Mosca server started.

Start the Frontend

cd webservice/frontend
npm install
npm start

or

npm run dev

open the link http://localhost:3000

For Windows

Initialize OpenVINO Environment

cd C:\Program Files (x86)\IntelSWTools\openvino\bin\ 

setupvars.bat

In the directory run:

python src/app.py -fdm models/intel/face-detection-adas-binary-0001/INT1/face-detection-adas-binary-0001 -erm models/intel/emotions-recognition-retail-0003/FP16/emotions-recognition-retail-0003 -agr models/intel/age-gender-recognition-retail-0013/FP16/age-gender-recognition-retail-0013  -i CAM -extension "{your openvino directory}/deployment_tools/inference_engine/bin/intel64/Release/cpu_extension_avx2.dll" -pt 0.4 -flags fdm erm agr 

Documentation for running command

• -fdm for face detection model
• -erm for emotion recognition model
• -agr for age gender recognition model
• -i is for input file (picture, video and cam)
• -extension for cpu extension which is needed for unsupported layers
• -d device type (CPU, GPU, VPU, FPGA)
• For more information you can run python src/app.py --help