Skip to content

SayantikaLaskar/COVID19-Image-Classification-Models-using-CNN-VGG16-ResNet50-Xception

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

COVID19-Image-Classification-Models-using-CNN-VGG16-ResNet50-Xception

Description:

🌟 Welcome to the COVID19-Image-Classification-Models Project! 🌟

In this repository, we tackle the pressing issue of COVID-19 detection using deep learning techniques! This project focuses on classifying medical images into three distinct categories: COVID-19, Normal, and Viral Pneumonia. By leveraging the power of convolutional neural networks (CNNs) and various pre-trained models, we aim to contribute to the ongoing battle against the pandemic through innovative technology.

🔍 Project Overview:

  • Deep Learning Architectures:

    • Utilize cutting-edge pre-trained models such as VGG16, Xception, and ResNet50 to analyze and classify images effectively.
    • Implement a custom Convolutional Neural Network (CNN) architecture for a hands-on approach to model design and training.
  • Comprehensive Data Processing:

    • Use ImageDataGenerator for real-time data augmentation and preprocessing, enhancing the robustness of our models.
  • Training and Evaluation:

    • Train models with extensive datasets while monitoring performance metrics.
    • Evaluate model accuracy and visualize results using loss and accuracy plots.
  • Performance Metrics:

    • Calculate and display important metrics such as:
      • Accuracy 📈
      • Precision 🎯
      • Recall 📊
      • F1 Score 🥇
      • Confusion Matrix 📉
      • AUC-ROC Curve 📈🔍

🛠️ Technologies Used:

  • Python 🐍
  • TensorFlow & Keras 🧠
  • Matplotlib & Seaborn 📊
  • Scikit-learn 📚

🚀 How to Use:

  1. Data Preparation: Download the COVID-19 image dataset and organize it into training and testing directories.
  2. Run the Models: Execute the provided Jupyter Notebook or Python scripts to train the models on the dataset.
  3. Visualize Results: View performance metrics and graphs to analyze the models' effectiveness.

🧪 Results:

Expect to see detailed classification reports and visualizations of model performance, showcasing how well each architecture performs on the dataset. This project aims to not only achieve high accuracy but also to provide a deeper understanding of the underlying models.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published