Chapter 1: Introduction to PyTorch
- Lesson 1: What is PyTorch?
- Lesson 2: PyTorch vs TensorFlow: A Comparison
- Lesson 3: Installing PyTorch (Windows, macOS, Linux)
- Lesson 4: Importing PyTorch and Checking Installation
- Lesson 5: Understanding PyTorch's Ecosystem (Torch, TorchVision, TorchAudio)
Chapter 2: PyTorch Tensors Basics
- Lesson 1: What are Tensors?
- Lesson 2: Creating Tensors (Scalar, Vector, Matrix, N-Dimensional)
- Lesson 3: Tensor Data Types and Conversions
- Lesson 4: Indexing, Slicing, and Reshaping Tensors
- Lesson 5: Broadcasting in PyTorch
Chapter 3: Tensor Operations
- Lesson 1: Arithmetic Operations on Tensors
- Lesson 2: Element-wise Operations
- Lesson 3: Matrix Multiplication and Dot Products
- Lesson 4: Applying Mathematical Functions (sin, exp, log)
- Lesson 5: Concatenation, Stacking, and Splitting
Chapter 4: Working with PyTorch Autograd
- Lesson 1: Understanding Autograd and Computational Graphs
- Lesson 2: Creating Tensors with Gradients
- Lesson 3: Backpropagation and Gradient Calculation
- Lesson 4: Freezing and Detaching Gradients
- Lesson 5: Using torch.no_grad() for Inference
Chapter 5: PyTorch Neural Network Modules
- Lesson 1: Introduction to torch.nn
- Lesson 2: Creating a Custom Neural Network
- Lesson 3: Understanding Activation Functions
- Lesson 4: Using Sequential and Module Classes
- Lesson 5: Forward and Backward Propagation
Chapter 6: Working with PyTorch Datasets and DataLoaders
- Lesson 1: Introduction to PyTorch Datasets
- Lesson 2: Using Built-in Datasets (MNIST, CIFAR-10)
- Lesson 3: Creating Custom Datasets
- Lesson 4: Using DataLoaders for Batch Processing
- Lesson 5: Data Augmentation with torchvision.transforms
Chapter 7: Loss Functions and Optimization in PyTorch
- Lesson 1: Introduction to Loss Functions
- Lesson 2: Mean Squared Error and Cross Entropy Loss
- Lesson 3: Introduction to Optimizers (SGD, Adam, RMSprop)
- Lesson 4: Learning Rate Schedulers
- Lesson 5: Implementing Backpropagation with PyTorch
Chapter 8: Training a Simple Neural Network
- Lesson 1: Defining a Model
- Lesson 2: Setting Up the Training Loop
- Lesson 3: Evaluating Model Performance
- Lesson 4: Handling Overfitting and Underfitting
- Lesson 5: Saving and Loading Models
Chapter 9: PyTorch for Computer Vision
- Lesson 1: Introduction to Image Processing with PyTorch
- Lesson 2: Using torchvision for Image Data
- Lesson 3: Pretrained Models with torchvision.models
- Lesson 4: Transfer Learning for Image Classification
- Lesson 5: Object Detection with Faster R-CNN
Chapter 10: PyTorch for Natural Language Processing (NLP)
- Lesson 1: Working with Text Data in PyTorch
- Lesson 2: Word Embeddings with torch.nn.Embedding
- Lesson 3: Implementing a Simple RNN
- Lesson 4: Using Pretrained Embeddings (Word2Vec, GloVe)
- Lesson 5: Sentiment Analysis with LSTMs
Chapter 1: Advanced Autograd and Computational Graphs
- Lesson 1: Understanding PyTorch’s Dynamic Computation Graph
- Lesson 2: Creating and Modifying Computational Graphs
- Lesson 3: Custom Autograd Functions
- Lesson 4: Checking Gradients with torch.autograd.gradcheck
- Lesson 5: Visualizing Computational Graphs
Chapter 2: Advanced Neural Network Architectures
- Lesson 1: Understanding CNNs in PyTorch
- Lesson 2: Implementing Residual Networks (ResNet)
- Lesson 3: Understanding and Implementing GANs
- Lesson 4: Transformers in PyTorch
- Lesson 5: BERT and GPT Models in PyTorch
Chapter 3: Model Performance and Optimization Techniques
- Lesson 1: Gradient Clipping and Vanishing Gradients
- Lesson 2: Batch Normalization and Dropout
- Lesson 3: Weight Initialization Strategies
- Lesson 4: Mixed Precision Training
- Lesson 5: Memory Optimization for Large Models
Chapter 4: Working with Large Datasets and Data Pipelines
- Lesson 1: Handling Large Datasets Efficiently
- Lesson 2: Using TorchData and WebDataset
- Lesson 3: Data Augmentation Best Practices
- Lesson 4: Multi-GPU Data Loading Strategies
- Lesson 5: Streaming and Lazy Loading Techniques
Chapter 5: PyTorch for Reinforcement Learning
- Lesson 1: Introduction to Reinforcement Learning with PyTorch
- Lesson 2: Implementing Deep Q-Networks (DQN)
- Lesson 3: Policy Gradient Methods
- Lesson 4: Using OpenAI Gym with PyTorch
- Lesson 5: Multi-Agent Reinforcement Learning
Chapter 6: Deploying PyTorch Models
- Lesson 1: Exporting Models with torch.jit
- Lesson 2: Serving Models with TorchServe
- Lesson 3: Deploying Models on AWS, GCP, and Azure
- Lesson 4: Edge AI with PyTorch Mobile
- Lesson 5: ONNX and TensorRT Optimization
Chapter 7: Working with Distributed Training
- Lesson 1: Introduction to Distributed Training
- Lesson 2: Data Parallelism vs Model Parallelism
- Lesson 3: PyTorch Distributed RPC Framework
- Lesson 4: Multi-GPU and Multi-Node Training
- Lesson 5: Debugging and Profiling Distributed Models
Chapter 8: Generative AI and PyTorch
- Lesson 1: Variational Autoencoders (VAEs)
- Lesson 2: Style Transfer with CNNs
- Lesson 3: Generative Adversarial Networks (GANs)
- Lesson 4: Diffusion Models with PyTorch
- Lesson 5: Text-to-Image Models (Stable Diffusion)
Chapter 9: PyTorch and Quantum Machine Learning
- Lesson 1: Introduction to Quantum Computing with PyTorch
- Lesson 2: Using PennyLane with PyTorch
- Lesson 3: Hybrid Classical-Quantum Models
- Lesson 4: Implementing Quantum Neural Networks
- Lesson 5: Quantum Generative Models
پیام شما
