In this project, we train a deep learning model that detects viral pneumonia based on chest X-rays. The input is an image-like data and the task is a computer-vision subject.
The input data contains two types of classes of images, Pneumonia, and normal. These are the two categories of X-rays that the model
will learn and predict. Also, having a relatively important size of data, we decide to use it to train a Convolutional Neural
Network from scratch. Some data augmentation techniques are used to increase the size of the dataset.
The notebook notebooks/cnntrainingcolab.ipynb
contains the main code to train the deep learning model.
clone the repository, create a virtual environment and install the dependencies.
For Windows users, you can run the following commands:
git clone https://github.com/deepanshu-yadav/Pneumonia_Classifier.git
python -m virtualenv .venv
.venv\Scripts\activate
pip install -r .\requirements.txt
The trained CNN is saved in a cnn_model.h5
file that can be used to test some X-ray images.