Skip to content

This repository contains the implementation of a Convolutional Neural Network (CNN) with attention mechanisms for the detection of Pneumonia from chest X-ray images.

License

Notifications You must be signed in to change notification settings

LikithMeruvu/Pneumonia-detection-Using-CNN

Repository files navigation

Pneumonia Detection Using CNN with Attention 👀

Welcome to the Pneumonia Detection project! This repository contains code for training a Convolutional Neural Network (CNN) with attention mechanism to detect pneumonia from chest X-ray images. Below, you'll find information on the dataset used for training, how to access the trained model, and where to find the hosted application.

Dataset

For training the pneumonia detection model, the Chest X-ray Images (Pneumonia) dataset from Kaggle was used. This dataset contains X-ray images of healthy and pneumonia-infected lungs.

Hosted Application

The trained model is hosted on the Hugging Face Spaces platform. You can access the application here. The application allows you to upload a chest X-ray image and get predictions on whether pneumonia is detected.

Model Access

Due to the large size of the model files (2.5GB each), it's recommended to access the model through the Hugging Face hosted space. You can download the model from the provided link in the application space.

Getting Started

  1. Clone this repository to your local machine:
git clone https://github.com/your-username/Pneumonia-detection-Using-CNN-attension.git
  1. Install the required dependencies:
pip install -r requirements.txt
  1. Run the application script:
python app.py
  1. Navigate to http://localhost:5000 in your web browser to access the application locally.

Contributing

Contributions to improve the model, add features to the application, or fix bugs are welcome! Please open an issue to discuss proposed changes or submit a pull request directly.

License

This project is licensed under the MIT License - see the LICENSE file for details.

👨‍💻 Happy pneumonia detection! If you have any questions or need assistance, feel free to reach out.