This repository is a complete PyTorch learning destination. It contains 14 detailed modules with hands-on Jupyter notebooks, practical implementations, and real-world projects covering the entire PyTorch ecosystem.
From fundamental tensor operations to building complex neural networks for computer vision, natural language processing, and sequential data modeling, this repository provides a structured learning path with theory, code, and practical applications.
# Clone the repository
git clone https://github.com/avinashyadav16/PyTorch.git
cd PyTorch
# Set up environment
python -m venv .venv
# Activate (Windows)
.venv\Scripts\activate
# Activate (Mac/Linux)
source .venv/bin/activate
# Install essential dependencies
pip install -r requirements.txt
# Start learning!PyTorch
├── 📂 01 Introduction to PyTorch
│ ├── 📄 1.0 INTRODUCTION TO PyTorch.pdf
│ ├── 📄 1.1 CORE FEATURES.pdf
│ ├── 📄 1.2 PyTorch VS TensorFlow.pdf
│ ├── 📄 1.3 PyTorch CORE MODULES.pdf
│ └── 📄 1.4 WHO USES PyTorch.pdf
│
├── 📂 02 Tensors in PyTorch
│ ├── 📄 2.0 TENSORS IN PyTorch.pdf
│ ├── 📄 2.1 WHY ARE TENSORS USEFUL.pdf
│ └── 📓 Tensors_In_PyTorch.ipynb
│
├── 📂 03 PyTorch autograd
│ ├── 📄 3.0 OVERVIEW PyTorch autograd.pdf
│ ├── 📄 3.1 WHAT IS autograd.pdf
│ └── 📓 PyTorch_autograd.ipynb
│
├── 📂 04 PyTorch Training Pipeline
│ └── 📓 pytorch_training_pipeline.ipynb
│
├── 📂 05 PyTorch NN Module
│ ├── 📄 5.0 PyTorch nn.Module.pdf
│ ├── 📄 5.1 The torch.optim module.pdf
│ ├── 📓 01 pytorch_nn_module.ipynb
│ ├── 📓 02 pytorch_training_pipeline_using_nn_module.ipynb
│ ├── 📓 pytorch_nn_module.ipynb
│ └── 📓 pytorch_training_pipeline_using_nn_module.ipynb
│
├── 📂 06 Dataset & DataLoader Class in PyTorch
│ ├── 📄 6.0 NEED OF Dataset & DataLoader CLASS.pdf
│ ├── 📄 6.1 Dataset & DataLoader CLASS IN PyTorch.pdf
│ ├── 📄 6.2 NOTE ABOUT DATA TRANSFORMATIONS.pdf
│ ├── 📄 6.3 NOTE ABOUT PARALLELIZATION.pdf
│ ├── 📄 6.4 NOTE ABOUT Samplers.pdf
│ ├── 📄 6.5 NOTE ABOUT collate_fn.pdf
│ ├── 📄 6.6 DataLoader IMPORTANT PARAMETERS.pdf
│ ├── 📓 dataset_and_dataloader.ipynb
│ ├── 📓 pytorch_training_pipeline_using_dataset_and_dataloader.ipynb
│ └── 📓 Simple_dataset_and_dataloader.ipynb
│
├── 📂 07 Building a ANN using PyTorch
│ ├── 📄 7.0 BUILDING A ANN/MLP USING PyTorch.pdf
│ ├── 📓 ann_fashion_mnist_pytorch.ipynb
│ └── 📊 fmnist_small.csv
│
├── 📂 08 Neural Network Training on GPU
│ ├── 📓 01_Steps_For_Training_A_Model_On_GPU.ipynb
│ └── 📓 02_Training_ANN_On_GPU.ipynb
│
├── 📂 09 Optimizing The Neural Network
│ ├── 📄 9.0 OPTIMIZING THE NEURAL NETWORK.pdf
│ ├── 📄 9.1 SOLUTION - DROPOUTS.pdf
│ ├── 📄 9.2 SOLUTION - BATCH NORMALIZATION.pdf
│ ├── 📄 9.3 SOLUTION - REGULARIZATION.pdf
│ └── 📓 GPU_Optimised_ANN.ipynb
│
├── 📂 10 Hyperparameter Tuning of ANN Using Optuna
│ ├── 📄 10.0 BAYESIAN HYPERPARAMETER TUNING METHOD USING Optuna - [ EXTRA ].pdf
│ └── 📓 10.1 BAYESIAN HYPERPARAMETER TUNING METHOD USING Optuna - [ EXTRA ].ipynb
│
├── 📂 11 Building CNN Using PyTorch
│ ├── 📄 11.0 BUILDING A CNN USING PyTorch.pdf
│ ├── 📓 Building_CNN_Using_PyTorch.ipynb
│ ├── 📓 Hyperparameter_Tuning_Of_A_CNN_Using_Optuna.ipynb
│ └── 📊 fashion-mnist_train.csv
│
├── 📂 12 Transfer Learning Using PyTorch
│ ├── 📄 12.0 TRANSFER LEARNING USING PyTorch.pdf
│ └── 📓 Transfer_Learning_using_PyTorch.ipynb
│
├── 📂 13 RNN Using PyTorch And Question Answering System
│ ├── 📄 13.0 RNN USING PyTorch & RNN BASED QUESTION ANSWERING SYSTEM.pdf
│ ├── 📓 RNN_BASED_QUESTION_ANSWERING_SYSTEM_USING_PYTORCH.ipynb
│ └── 📊 100_Unique_QA_Dataset.csv
│
├── 📂 14 LSTM And Next Word Predictor Using Pytorch
│ ├── 📄 14.0 NEXT WORD PREDICTOR USING PyTorch & LSTM USING PyTorch.pdf
│ └── 📓 PyTorch_LSTM_Next_Word_Prediction_Model.ipynb
│
├── 📂 DATASETS
│ ├── 📊 100_Unique_QA_Dataset.csv
│ ├── 📊 fmnist_small.csv
│ └── 📄 Dataset.md
│
├── 📄 LICENSE
├── 📄 README.md
└── 📄 requirements.txt
- Practical Deep Learning using PyTorch By CampusX for the whole learning.
- PyTorch Team for the amazing framework
- Fashion-MNIST for the benchmark dataset
- Optuna for hyperparameter optimization tools
⭐ Star this repository if you find it helpful!
Made with ❤️ by Avinash Yadav