https://github.com/arezyhs/python-mnist-classification

https://github.com/arezyhs/python-mnist-classification

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/arezyhs/python-mnist-classification
• Owner: arezyhs
• Created: 2024-11-29T18:23:19.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2024-11-30T15:57:11.000Z (about 1 month ago)
• Last Synced: 2024-11-30T16:31:06.890Z (about 1 month ago)
• Language: Jupyter Notebook
• Size: 1.32 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Handwritten Digit Recognition with KNN and MLP

This repository contains a Python code to train and evaluate machine learning models on the **MNIST dataset**, a collection of handwritten digits. It uses two models:

1. **K-Nearest Neighbors (KNN)**

2. **Multilayer Perceptron (MLP)**

The models are trained and evaluated using the MNIST dataset, and the performance is assessed using confusion matrices and accuracy metrics. Additionally, the code allows users to upload an image of a handwritten digit and make predictions using the trained models.

## Features

- **KNN and MLP Models**: Implements two machine learning algorithms, KNN and MLP, to classify handwritten digits.

- **Model Evaluation**: The models are evaluated using accuracy and confusion matrices.

- **Image Upload for Prediction**: Users can upload their own handwritten digit images to see how the models perform on unseen data.

- **Heatmaps**: Visualizes the confusion matrix as heatmaps for both models.