StyleSense is a Convolutional Neural Network (CNN) built using PyTorch to classify images from the Fashion MNIST dataset. This project demonstrates the process of building, training, and evaluating deep learning models for image recognition.
This notebook explores the development of different neural network architectures, starting with a simple linear model and progressing to a more complex CNN. The goal is to accurately classify images of clothing items and accessories from the Fashion MNIST dataset.
- PyTorch: Deep learning framework for model development and training.
- torchvision: For dataset handling (Fashion MNIST) and image transformations.
- torch.utils.data.DataLoader: For efficient data loading and batching.
- torch.nn: To define model layers and architectures.
- torch.optim: For model optimization (SGD).
- torchmetrics & mlxtend: For comprehensive model evaluation, including Confusion Matrix.
- matplotlib: For data and results visualization.
- pandas: For comparing model performance metrics.
- Python: The core programming language.
To run this notebook, you will need to have Python and the necessary libraries installed.