This repository contains the implementation of Convolutional Neural Networks (CNNs) for recognizing COVID-19 from medical images, developed by Mafizur Rahman on April 21, 2024.
The project applies deep learning techniques to detect the presence of COVID-19 in medical imagery. Three different CNN structures have been tested and evaluated to determine the most accurate model.
The dataset used in this project is the covidNetDataset, which consists of medical images labeled as either "Positive" or "Negative" for the presence of COVID-19.
- Python
- TensorFlow
- Keras
- NumPy
- Matplotlib
- Seaborn
- scikit-learn
To run this project, first clone the repo on your device using the command below:
git clone https://github.com/yourusername/covid-recognition-cnn.git
## Models
The repository includes three different CNN architectures for you to explore. Each model's structure and performance metrics are documented within the notebook.
## Results
Evaluation metrics such as accuracy, precision, recall, F1 score, and confusion matrices for each model are available in the notebook for analysis.
## K-Fold Validation
K-Fold Cross-Validation is used to ensure the robustness of the models. The results are documented within the notebook.
## Contributing
If you'd like to contribute, please fork the repository and use a feature branch. Pull requests are warmly welcome.