Deep Learning Course - PyTorch

Welcome to the Deep Learning Course - PyTorch! This course is designed to provide you with a comprehensive understanding of deep learning concepts using the PyTorch framework. Whether you are a beginner or an experienced practitioner, this repository contains valuable resources to enhance your knowledge and skills in deep learning.

Table of Contents

1. Course Overview
2. Course Structure
3. Getting Started
4. Course Materials
5. Requirements
6. License
7. Contact

Course Overview

In this course, we will cover the following key topics:

• PyTorch fundamentals
• Multi-layer Perceptrons (MLP)
• Convolutional Neural Networks (CNN)
• Advanced topics such as ResNet architectures

Course Structure

The course is organized into the following sections:

• Section 1: Mastering PyTorch
  • Introduction to PyTorch and its fundamentals.
  • Practical exercises using PyTorch.
• Section 2: Multi-layer Perceptrons (MLP)
  • Hands-on project using MLP to analyze the Titanic dataset.
• Section 3: Convolutional Neural Networks (CNN)
  • Practical implementations on various benchmark datasets (e.g., CIFAR).
  • Building a ResNet from scratch.

Getting Started

To get started with this course, clone the repository to your local machine:

git clone https://github.com/ebimsv/Deep-learning-course-PyTorch.git
cd Deep-learning-course-PyTorch

Open the Jupyter notebooks in the notebooks directory to follow along with the course materials.

Course Materials

The course materials are organized as follows:

• index.md: Course outline and navigation document.
• LICENSE: Licensing information for the materials.
• notebooks/: Contains Jupyter notebooks for each section of the course.
  • 01_Mastering_PyTorch/: Fundamentals of PyTorch.
  • 02_MLP/: Titanic MLP analysis.
  • 03_CNN/: CNN implementations, including various datasets and models.
• pics/: Images and figures used throughout the course.
• projects/: Additional project ideas and resources.
• requirements.txt: List of required Python packages for running the notebooks.
• src/: Source code for any utility functions or classes used in the course.

Requirements

Before you start, ensure you have the necessary dependencies installed. You can easily set up the environment with:

pip install -r requirements.txt

License

This course is licensed under the MIT License. See the LICENSE file for more details.

Contact

For any questions or feedback, please reach out to [email protected].

Happy Learning!