This project focuses on developing a CNN model for pneumonia diagnosis using chest X-ray images. The model achieved an accuracy of 90.54% on the test dataset.
- Train dataset: 5216 samples
- Validation dataset: 16 samples
- Test dataset: 624 samples
The dataset used for this project can be found here.
The model consists of convolutional layers, batch normalization, activation functions, max pooling, flattening, dense layers, dropout, and an output layer.
- Training loss: 0.2709
- Training accuracy: 90.54%
To run the notebook and reproduce the results:
- Clone the repository
- Install dependencies
- Open the notebook file
- Run the notebook cells sequentially
The Kaggle notebook for this project can be found here.