This project features a custom-built Convolutional Neural Network (CNN) for classifying the Fashion MNIST dataset.

Fashion MNIST Classification with Custom CNN in PyTorch

🚀 Project Overview

This project implements a custom CNN architecture for classifying the Fashion MNIST dataset, which contains 70,000 grayscale images across 10 clothing categories such as t-shirts, coats, and sneakers.

🛠️ Key Features

• Custom CNN Architecture: Built from scratch using PyTorch
• Skip Connections: Improve gradient flow and feature extraction
• Learning Rate Scheduling: Optimize training convergence
• **Comprehensive Model Evaluation: Confusion Matrix (You can use Precision or Recall)
• Hyperparameter Tuning: Achieve optimal training performance

📊 Model Performance

Metric	Value
Training Accuracy	95%
Test Accuracy	93%

📁 Dataset

The dataset used is Fashion MNIST, available directly in torchvision.datasets.FashionMNIST.

⚙️ How to Run the Project

1. Clone the repository:

   git clone <https://github.com/AlirezaChahardoli/Fashion-MNIST-Classification-with-PyTorch.git>