--Overview--
This repository contains my practice work and learning materials for PyTorch. It includes Jupyter Notebook files where I implement fundamental concepts of deep learning, neural networks, and computer vision using PyTorch. The goal of this repository is to strengthen my understanding of deep learning frameworks and build practical experience with model development and training.
--Repository Contents--
PyTorch_1.ipynb Introduction to PyTorch basics including tensors, operations, automatic differentiation (Autograd), and simple neural network implementation.
MNIST_Project.ipynb Implementation of a neural network model for handwritten digit classification using the MNIST dataset. Includes data preprocessing, model building, training, and evaluation.
CNN_Vision.ipynb Convolutional Neural Network (CNN) implementation for computer vision tasks. Covers convolution layers, activation functions, pooling layers, and model performance evaluation.
--Technologies Used-- Python PyTorch NumPy Matplotlib Jupyter Notebook
--Learning Objectives-- Understand PyTorch tensor operations and computational graphs Build and train neural network models Implement Convolutional Neural Networks
Perform image classification tasks
Evaluate and improve model performance