Skip to content

shibinjudahpaul/Machine-and-Deep-Learning-Projects

Repository files navigation

Machine and Deep Learning Portfolio

This is my portfolio of Machine and Deep Learning projects. Each project includes a brief overview, the tools and technologies used, and the outcomes achieved. All of the code and relevant datasets are available in the corresponding project repository.

Table of Contents

Project 1: Chest X-ray detector using VGG16

This is a deep learning project where I have trained a convolutional neural network (CNN) to classify chest X-ray images into two categories: COVID-positive and COVID-negative. The model was built using TensorFlow and Keras and achieved an accuracy of 98% on the test set.

Project 2: Comparision of 4 CNN models on 2 Datasets

This is a Kaggle notebook where I have experimented with four different convolutional neural network (CNN) models for a classic binary classification problem: cats vs. dogs.

Project 3: Face Mask Detector using Transfer learning and Mobilenet v2

This is a Kaggle notebook where I've leveraged three different models, a Deep Neural Network (DNN) model published in OpenCV's GitHub that can detect faces, and a basic Convolutional Neural Network (CNN) and MobileNet v2, which are trained on a dataset of masked and unmasked people.

Dependencies

The projects in this repository use the following dependencies:

  • Python 3.x
  • TensorFlow 2.x
  • OpenCV
  • NumPy
  • Matplotlib
  • Keras

You can install these dependencies using pip.

pip install tensorflow opencv-python numpy matplotlib 

Usage

Each project is contained in its own directory, and includes a README file with detailed instructions on how to run the project and use its functionalities.

Conclusion

This Machine and Deep Learning Portfolio showcases my skills and expertise in various aspects of machine learning, such as data preprocessing, exploratory data analysis, feature engineering, model selection, and evaluation. I have implemented various projects using popular libraries such as TensorFlow and OpenCV, and have included detailed instructions on how to use and run each project.