CNN Architecture Optimization

Project Overview

This project focuses on the iterative improvement of Convolutional Neural Network (CNN) architectures, specifically variants of the LeNet-5 model, for image classification using the FashionMNIST dataset.

Key Objectives

  1. Implement the original LeNet-5 architecture from scratch using PyTorch
  2. Develop and evaluate successive variants of LeNet-5, each building upon the previous version
  3. Optimize model performance for the FashionMNIST classification task
  4. Gain insights into the impact of architectural modifications on CNN performance

Methodology

  1. Base Implementation:
    • Recreate the LeNet-5 architecture using PyTorch
  2. Iterative Improvement:
    • Design and implement variants of LeNet-5
    • Each variant aims to enhance performance over its predecessor
  3. Training and Validation:
    • Utilize the FashionMNIST dataset for model training and evaluation
  4. Performance Tracking:
    • Employ Weights & Biases (wandb) for comprehensive performance monitoring and analysis
  5. Architectural Optimization:
    • Systematically modify network architecture to improve classification accuracy

Tools and Technologies

  • PyTorch: Deep learning framework
  • FashionMNIST: Modern benchmark dataset for image classification
  • Weights & Biases: Experiment tracking and visualization

Resources