PyTorch for Deep Learning & Machine Learning

This repository contains a collection of Jupyter Notebooks implementing concepts and exercises (mostly from "PyTorch for Deep Learning" course by Daniel Bourke). The notebooks offer a practical and interactive approach to mastering PyTorch for various deep learning tasks.

Topics Covered:

• PyTorch Fundamentals: Dive into tensors, tensor operations, and automatic differentiation – the building blocks of deep learning with PyTorch.
  • Notebook 00
• Neural Networks: Building neural networks from scratch, understanding layers and activation functions
  • Notebook 01
• Image Classification: Working with convolutional neural networks (CNNs), the powerhouse behind image recognition, training your own image classifiers
• Natural Language Processing (NLP): Exploring recurrent neural networks (RNNs) and other NLP techniques
• Model Training and Evaluation: Grasp the essentials of Optimizers, loss functions, training loops and evaluating model performance.
• Advanced Concepts: Go beyond the basics with Transfer learning, model deployment, and more..

Requirements:

Option 1: Local Machine Setup

• Python 3.x: Verify your version by running python --version in your terminal. If you don't have Python 3, download it from https://www.python.org/downloads/.
• PyTorch: Follow the installation instructions: https://pytorch.org/get-started/locally/.
• NumPy: Install NumPy using pip install numpy in your terminal.
• Matplotlib: Install Matplotlib using pip install matplotlib in your terminal.

Option 2: Google Colab

1. Visit https://colab.research.google.com.
2. This environment already includes Python, PyTorch, NumPy, and Matplotlib. No local installation is required.
3. Upload the contents of this repository to your Colab notebook for execution.

Usage: Choose Your Environment:

1. Google Colab: Upload the repository's contents to a new Colab notebook.
2. VS Code with Jupyter Notebook: Clone the repository, open it in VS Code, and double-click on a .ipynb file to run.
3. Jupyter Notebook:
   • Navigate to the repository's directory in your terminal.
   • Run jupyter notebook. This will open the Jupyter Notebook interface in your browser.
   • Open and run the notebooks (.ipynb files).

To run the notebooks, double-click on each .ipynb file in your chosen environment.

An Even more better Option

Create a new folder, then a new .py or .ipynb file in your code editor or IDE and start coding, follow through with the tutorial, make some edits, tweak some values along the way, encounter some issues/bugs, resolve them and by the end you'll have developed an intution for the key concepts.

References:

• Resources that inspired this project:
  • https://www.learnpytorch.io/
  • Daniel Bourke PyTorch YouTube Series or
  • PyTorch for Deep Learning & Machine Learning – Full Course (freeCodeCamp.org)
  • Essence of Linear Algebra by 3blue1brown

License:

• Fully open source (Experiment with it as you see fit)