π¦ Pneumonia Classification Model
Welcome to the Pneumonia Classification Model repository! This project utilizes a deep learning approach based on the powerful ResNet-18 architecture to classify chest X-ray images and detect pneumonia with high accuracy.
π Project Overview
This repository contains code for:
- Training a ResNet-18 model for pneumonia classification
- Evaluating model performance with detailed accuracy metrics
- Visualizing key features using Class Activation Mapping (CAM)
π Key Features
β
ResNet-18 Backbone: Fine-tuned on chest X-ray images for accurate pneumonia detection
β
Model Evaluation: Includes both weighted and non-weighted accuracy assessments
β
Class Activation Mapping (CAM): Visualizes critical regions influencing the modelβs predictions
β
Efficient Training: Optimized data pipelines for fast model training and inference
ποΈ Repository Structure
Pneumonia-Classification-Model/
βββ PneumoniaClassification.ipynb # Jupyter Notebook for model training & evaluation
βββ checkpoints/ # Saved model weights
βββ data/ # Dataset folder (chest X-ray images)
βββ outputs/ # Generated CAM images & evaluation results
βββ README.md # Project documentation
βοΈ Installation
- Clone the Repository:
git clone https://github.com/SYEDFAIZAN1987/Pneumonia-Classification-using-resnet-18-based-model-with-evaluation-and-CAM.git
cd Pneumonia-Classification-Model
- Install Dependencies:
pip install -r requirements.txt
- Run the Model:
jupyter notebook PneumoniaClassification.ipynb
π Model Performance
Non-Weighted Accuracy:
Weighted Loss Accuracy:
Class Activation Mapping (CAM):
Visual representation of regions critical to the modelβs pneumonia classification:
π Evaluation Metrics
- Precision, Recall, F1-Score for performance evaluation
- Confusion Matrix for classification analysis
- Weighted vs Non-Weighted Accuracy comparison
π€ Contributing
Contributions are welcome! To contribute:
- Fork the repository
- Create a new branch:
git checkout -b feature-branch
- Commit your changes
- Open a pull request π
π License
This project is licensed under the MIT License.
π¨ββοΈ Author
Developed by Syed Faizan
For any queries or collaborations, feel free to connect on GitHub.
β If you found this project useful, please give it a star! β
Model tree for DrSyedFaizan/Pneumofind
Base model
frgfm/resnet18