This repository contains a simple implementation of a neural network built from scratch using Numpy. The neural network is trained to classify pneumonia images into two categories: normal and pneumonia.
-
Clone the repository:
git clone https://github.com/tu_usuario/tu_repositorio.git
-
Navigate to the project directory:
cd tu_repositorio
-
Install the required dependencies (it is recommended to use a virtual environment):
pip install -r requirements.txt
-
Run the main script to train the neural network:
python main.py
The dataset consists of X-ray images of lungs with and without pneumonia. The images are categorized into two classes: normal and pneumonia.
You can access the dataset on Kaggle.
The project is organized as follows:
- neural_network: Contains the implementation of the neural network.
- neural_network.py: Defines the NeuralNetwork class with methods for training and inference.
- create_data.py: Provides functionality for loading and formatting the dataset.
- main.py: Script to train the neural network using the dataset.
- Python 3
- Numpy
- OpenCV
- Matplotlib
- Scipy (Only for the sigmoid equation) TODO: Do the sigmoid equation only with Numpy
This project is licensed under the MIT License - see the LICENSE file for details.
Author Santiago (santiagosaav.99@gmail.com)
Feel free to reach out with any questions or feedback!