Deep Vision Project IWR University Heidelberg

• About the Project
  • Built With
• Getting Started
  • Prerequisites
  • Installation
• Roadmap
• License

Project has been developed as final exam for Deep Vision. Detection of infected patients is an important task, expecially with the current Covid-19 pandemic. We want to explore the possibility of applying machine learning techniques to determine whether a patient is infected based on a X-Ray images of his lungs.

• PyTorch
• COVID-19 image data collection
• NIH
• Torchxrayvision

To get a local copy up and running follow these simple steps.

First, you need to download the NIH dataset. You can use aria2c.

• Use aria2c to download NIH dataset

aria2c NIH-e615d3aebce373f1dc8bd9d11064da55bdadede0.torrent

• Unzip NIH images

tar -xzf images-224.tar.gz

• Move NIH images

mv ./images-224 {PATH_TO_DATA_FOLDER}/data/images-nih

• Get COVD-19 images

git clone https://github.com/ieee8023/covid-chestxray-dataset.git

• Get COVD-19 images

mv ./images {PATH_TO_DATA_FOLDER}/data/images-covid

1. Clone the repo

git clone https://github.com/stefanDeveloper/covid-19-neural-network.git

2. Run main

python main.py

See the open issues for a list of proposed features (and known issues).

Distributed under the MIT License. See LICENSE for more information.