🔥PyTorch: Noob to Proficient

Welcome to "PyTorch: Noob to Proficient"! This comprehensive course is designed to take you from a complete beginner to a proficient PyTorch programmer. Join us on this journey and master one of the most powerful deep learning frameworks!

📌 Notice

This is kind of my learning diary, where I am compiling a series of lessons that bring together all the knowledge I have acquired from various scattered sources, including books, articles, websites, YouTube videos, and more. My goal is to create a comprehensive course that consolidates this information, making it easier for others to access and learn from as they progress in their journey of learning the PyTorch from the basics to a level where they can confidently use it to build real deep learning applications. Hope this helps🙂

📑 Contents

Phase 1: PyTorch Fundamentals

01: Introduction to PyTorch

• What is PyTorch?
• Installing PyTorch
• Neural Networks and Tensors

02: PyTorch Basics

• PyTorch Fundamentals
• Basic Structure of PyTorch Model and Training Loop
• Example: Linear Regression

Phase 2: Building Neural Networks

03: Feedforward Neural Networks

• Fully Connected Layers
• Activation Functions
• Building a Simple Feedforward Neural Network
• Training and Evaluating Models
• Advanced Concepts
• Logistic Regression
• Multi-Class Classification

04: Convolutional Neural Networks (CNNs)

• Introduction to CNNs
• Architecture of CNNs
• Why Use CNNs?
• Components of CNNs
• CNN Layers Implementation
• Advanced CNN Architectures

05:Recurrent Neural Networks (RNNs)

• Introduction to RNNs
• RNN Fundamentals
• Building a Simple RNN
• Advanced RNN Variants

PROJECT 01: Bitcoin Price Prediction

06: Long Short-Term Memory (LSTM) Networks

• Introduction to LSTMs
• LSTMs Fundamentals
• Implementing simple LSTM with PyTorch
• LSTM Variants
• Hyperparameter tuning

07: Transformers

06: Transfer learning

Phase 4: Natural Language Processing

05: Natural Language Processing (NLP)

05: Word Embeddings

05: Sequence-to-Sequence Models

05: Transformers and Attention Mechanisms

Phase 5: Computer Vision

05: Image classification

05: Object detection

05: Semantic segmentation

Phase 3: Generative Models

06: Autoencoders

06: Variational Autoencoders (VAEs)

06: Generative Adversarial Networks (GANs)

06: Advanced Generative Models