ML Projects Repository

Welcome to my ML Projects repository! Here, you'll find a collection of Jupyter Notebook (.ipynb) files from various machine learning projects I've worked on. This repository serves as a showcase of my machine learning skills and a reference for anyone interested in exploring these projects. I have also included the majority of my kaggle notebooks in this repo along with their public links, so do upvote them if you find them helpful :)

Table of Contents

• Introduction
• Projects
• Usage
• Contributing
• License

Introduction

In this repository, I share machine learning projects that I've completed as part of my journey in the field of machine learning and data science. Each project is contained within a separate Jupyter Notebook, making it easy to explore, replicate, and learn from my work.

Feel free to browse through the projects and provide feedback or suggestions. I'm continuously learning and improving, and your input is valuable.

Projects

Here's a list of the projects available in this repository:

1. Car Classifier: A project that classifies a car image into either Ferrari, Mclaren or Mercedes using Computer Vision(using fastai library)
2. Reverse Image Search Using Image Captioning: Developeda Reverse Image Search with an Image Captioning model as the underlying architecture of the model. Transformer was used to develop the image encoder text decoder model to generate captions which provides the best accuracy compared to other RNN encoder-decoder models.

Each project is accompanied by a link to the corresponding Jupyter Notebook file, allowing you to dive into the details of the project. (More projects in the Kaggle Notebooks folder

Usage

You can use this repository in several ways:

• Exploration: Browse through the projects to gain insights into various machine learning techniques and application domains.
• Replication: If you find a project interesting, you can replicate it by following the steps outlined in the respective Jupyter Notebook.
• Learning: Use these projects as learning resources to understand how different machine learning concepts are applied in real-world scenarios.

Contributing

If you have suggestions, improvements, or would like to collaborate on a project, feel free to open an issue or submit a pull request. Your contributions are highly appreciated.

Happy exploring and learning!