This folder contains a series of Jupyter Notebooks designed to introduce you to the basics of PyTorch, a popular deep learning framework. Below is a brief summary of each notebook:
This notebook covers the basics of tensor operations in PyTorch. You will learn how to create tensors, perform basic and advanced operations, and understand tensor attributes such as shape, datatype, and device allocation.
This notebook introduces the concept of automatic differentiation in PyTorch. You will learn how to calculate gradients using the backward() function, understand the computational graph, and perform gradient-based optimization.
This notebook focuses on data handling in PyTorch. You will learn how to create custom datasets using the Dataset class and visualize data.
This notebook guides you through the process of creating a neural network in PyTorch. You will learn how to define a neural network architecture, perform forward and backward passes, and update model parameters using optimization techniques.
Each notebook is designed to build on the previous one, providing a comprehensive introduction to PyTorch. Happy learning!