https://github.com/sccsmartcode/deep-learning-00

Image Classification with CNNs
https://github.com/sccsmartcode/deep-learning-00

cnn computer-vision deep-learning image-classification machine-learning

Last synced: 19 days ago
JSON representation

Image Classification with CNNs

• Host: GitHub
• URL: https://github.com/sccsmartcode/deep-learning-00
• Owner: SCCSMARTCODE
• License: mit
• Created: 2024-05-23T08:46:49.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-09-19T13:18:09.000Z (almost 2 years ago)
• Last Synced: 2025-10-20T07:58:00.436Z (9 months ago)
• Topics: cnn, computer-vision, deep-learning, image-classification, machine-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 1.94 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Deep-Learning-00: Image Classification with Convolutional Neural Networks

![Deep learning](./Artificial-intelligence-Deep-Learning.png)

## Overview

This repository contains my implementation of a basic image classification project using Convolutional Neural Networks (CNNs) and transfer learning techniques. It serves as a foundational exploration of deep learning for image-related tasks.

## Project Purpose

The goal of this project is to demonstrate the application of CNNs for classifying images, utilizing well-known architectures and transfer learning methodologies. This approach allows for efficient training on smaller datasets by leveraging pre-trained models.

## Key Features

- **Convolutional Neural Networks**: Implementation of CNN architectures for effective feature extraction and classification.

- **Transfer Learning**: Utilizes pre-trained models (e.g., VGG16, ResNet) to improve performance on new datasets with limited samples.

- **Data Augmentation**: Applied techniques to enhance the dataset and improve model generalization.

- **Metrics Monitoring**: Integrated with Weights & Biases (WandB) for tracking training metrics and visualizations.

## Technologies Used

- **Framework**: PyTorch

- **Libraries**: NumPy, Matplotlib, WandB

- **Datasets**: MNIST, Cifar10, Cifar100, FashionMNIST, ASL_Alphabet

## Getting Started

### Prerequisites

Make sure you have the following installed:

- Python

- PyTorch

- WandB