https://github.com/pawlo77/mnist-computer-vision
Repository for Computer-Vision project of Data Science Academic Circle at Faculty of Mathematics and Information Science, Warsaw University of Technology
https://github.com/pawlo77/mnist-computer-vision
computer-vision data-science maschine-learning mnist
Last synced: 3 months ago
JSON representation
Repository for Computer-Vision project of Data Science Academic Circle at Faculty of Mathematics and Information Science, Warsaw University of Technology
- Host: GitHub
- URL: https://github.com/pawlo77/mnist-computer-vision
- Owner: Pawlo77
- Created: 2023-03-31T12:03:50.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-05-28T21:32:51.000Z (about 3 years ago)
- Last Synced: 2025-03-20T12:15:26.211Z (over 1 year ago)
- Topics: computer-vision, data-science, maschine-learning, mnist
- Language: Jupyter Notebook
- Homepage:
- Size: 3.7 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MNIST Computer Vision
The "mnist_cv" project is a comprehensive Computer Vision project that focuses on the MNIST dataset, a well-known dataset for digit classification.
## Project Goal
The primary objective of this project is to create and compare the performance of machine learning models for digit classification using the MNIST dataset. It aims to explore and evaluate both traditional machine learning algorithms and advanced deep learning models, providing insights into their effectiveness and performance in image recognition tasks.
## Technologies Used
The project leverages the following technologies and libraries:
- **Machine Learning Models**: The models are developed using the scikit-learn library for traditional machine learning algorithms and PyTorch for deep learning models. This combination allows for a comparison between different approaches and techniques.
- **Data Analysis**: Data analysis tasks are performed using Seaborn, Matplotlib, and Pandas libraries. These tools facilitate exploratory data analysis, visualization, and statistical analysis of the MNIST dataset.
- **Data Preprocessing**: Sklearn and NumPy libraries are used for data preprocessing tasks. This includes tasks such as feature scaling, dimensionality reduction, and data transformation to ensure optimal model performance.
By utilizing these technologies, the "mnist_cv" project enables a comprehensive analysis of digit classification using the MNIST dataset. It provides valuable insights into the performance of different machine learning models, offering a deeper understanding of their capabilities and limitations in the context of image recognition tasks.