Skip to content

Geronimo-Basso/digit-recognizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Digit Recognizer, 99.5% Accuracy, #85 in Kaggle leaderboard.

This repository contains the code for the Digit Recognizer project, which aims to accurately recognize handwritten digits using machine learning techniques. This project is part of the Kaggle Digit Recognizer competition.

image

Screenshot 2024-08-27 at 22 34 28

The goal of this project is to build a model that can correctly identify digits from a dataset of handwritten images. This is a classic problem in the field of computer vision and machine learning, often used as an introductory exercise for learning about neural networks and image processing. DatasetThe dataset used in this project is the MNIST dataset, which consists of 60,000 training images and 10,000 testing images of handwritten digits. Each image is 28x28 pixels in grayscale. I use a Convolutional Neural Network (CNN) to perform the digit recognition task. CNNs are particularly well-suited for image recognition tasks due to their ability to capture spatial hierarchies in images. InstallationTo run this project, you need to have Python installed along with the following libraries:

  • TensorFlow
  • Keras
  • NumPy
  • Matplotlib You can install the required libraries using the following command:
pip install tensorflow keras numpy matplotlib

Clone the repository:

git clone https://github.com/Geronimo-Basso/digit-recognizer.git

The model achieves an accuracy of over 99.5% on the MNIST upload competition. Contributions are welcome! Please open an issue or submit a pull request for any improvements or bug fixes.

About

Kaggle Digit Recognizer. 99.5% Accuracy. #85 out of 1550 in Kaggle leaderboard.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published