Skip to content

Priyanshu-C/COVID-DETECTION-USING-XRAY

Repository files navigation

COVID-DETECTION-USING-XRAY

Tech Stack -


  • This app has mutiple models you can predict the xray upon, we trained a model on over 9 CNN models with different layers setup along with pretrained model like VGG16 and VGG19.
  • OpenCV has been used to scale and resize the images to the required input size.
  • Deployment has been done on flask with very basic route and 2 html pages.

How to run?

OS X & Linux:

python app.py

Windows:

python app.py

Usage

  • This is an experimental project to better our understanding of the ImageProcessing using Neural Network.
  • This obviously can't be deployed in real-time, because even if we have reached the accuracy of over 98% but the dataset used to train was not large and the metadata classified the Covid and Pneumonia cases as the same.

Development setup

I have attached requirements.txt in the repository for better support, but majorly we the libraries involved are.

Flask 1.1.2
Keras 2.4.3
opencv-python 4.4.0.44
tensorflow 2.3.1
tensorboard 2.3.0

Model Trained to get the best number of layer setup for the project

EDA

  • Age Wise Pie-Chart

  • Correlation Heatmap

  • Table for all diseases

  • Histogram for all diseases

  • X-Ray Views Distribution

Meta

Priyanshu Chauhan –– [email protected]

https://github.com/Priyanshu-C/COVID-DETECTION-USING-XRAY

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published