https://github.com/ehvenga/mnist.handwritten.digit.recognition-tensorflow
This Jupyter Notebook demonstrates a TensorFlow model for recognizing handwritten digits using the MNIST dataset, focusing on model construction, training, and accuracy evaluation.
https://github.com/ehvenga/mnist.handwritten.digit.recognition-tensorflow
computer-vision convolutional-neural-networks handwritten-digit-recognition machine-learning mnist-classification tensorflow
Last synced: about 2 months ago
JSON representation
This Jupyter Notebook demonstrates a TensorFlow model for recognizing handwritten digits using the MNIST dataset, focusing on model construction, training, and accuracy evaluation.
- Host: GitHub
- URL: https://github.com/ehvenga/mnist.handwritten.digit.recognition-tensorflow
- Owner: ehvenga
- Created: 2024-04-19T08:57:54.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-19T19:42:23.000Z (about 2 years ago)
- Last Synced: 2025-03-20T21:17:47.890Z (over 1 year ago)
- Topics: computer-vision, convolutional-neural-networks, handwritten-digit-recognition, machine-learning, mnist-classification, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 321 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MNIST Digit Recognition using TensorFlow
## Overview
This repository contains a Jupyter Notebook that demonstrates the use of TensorFlow to recognize handwritten digits from the MNIST dataset. The project utilizes a convolutional neural network (CNN) for high accuracy in digit classification.
## Prerequisites
- Python 3.x
- TensorFlow 2.x
- NumPy
- Matplotlib (for visualization)
## Installation
To get started with this project, clone the repository to your local machine:
```bash
git clone https://github.com/your-username/mnist-digit-recognition.
jupyter notebook MNIST_Digit_Recognition.ipynb
```
## Dataset
The MNIST dataset comprises 70,000 grayscale images of handwritten digits (0-9), each of size 28x28 pixels. The dataset is split into 60,000 training images and 10,000 testing images.
## Model
The notebook details the CNN architecture used for digit classification, including layers, activation functions, and compilation strategy.
## Evaluation
Evaluation metrics are provided within the notebook to assess the accuracy and effectiveness of the trained model on test data.
## Contributing
Contributions to this project are welcome. Please fork the repository and submit pull requests to enhance the functionality or performance of the model.