/PneumoniaDetection

Primary LanguagePureBasic

Android Implementation

Android app (https://github.com/kartiksharmakk/PneumoniaDetection/tree/main/android) using Tensorflow Lite Support Library .

Apk can also be downloaded from Github Release of this repository

💁‍♂️ How to build Android Implementation locally

  • Clone The Repo and open Android Studio inside the android folder
  • Android Studio will sync the gradle and user can then run the app on Emulator

Web Implementation using Python Flask

https://github.com/kartiksharmakk/PneumoniaDetection/tree/main/web local implementation tested using conda terminal

Desktop.2022.08.26.-.23.11.27.02.mp4

💁‍♂️ How to build Web Implementation locally

  • Clone The Repo and open web directory
  • Install Python requirements pip install -r requirements.txt
  • Start the server for development python app.py or python3 app.py

Model Visualized

  • CNN Tensorflow Lite Model trained on https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia Dataset
  • Model Has An Accuracy of 92%
  • Model gives prediction within range of 0 (tending to normal) and 1 (tending to pneumonic) , to be sure that pneumonic people arent classified as normal , I have set parameter above 0.2 to denote pneumonic
  • Model files and The training jupyter notebook are present in model_generation.zip file