This project implements a Convolutional Neural Network (CNN) to detect pneumonia from chest X-ray images. The model is trained on a dataset containing normal and pneumonia-affected X-rays to classify images effectively.
The dataset used for training and evaluation is sourced from the Chest X-Ray Pneumonia dataset available on Kaggle. It consists of:
Normal X-rays: Healthy lung images.
Pneumonia X-rays: Images showing signs of pneumonia.
Implemented using PyTorch and Resnet18.
Data preprocessing includes normalization and augmentation.
Model architecture: Convolutional layers, batch normalization, and ReLU activation functions.
Evaluation using accuracy
Ensure you have the following dependencies installed:
Clone Repository
Train the Model
Test the Model
Run Web App (if applicable)
The CNN achieves an accuracy of approximately 92% on the test set.