Skip to content

Latest commit

 

History

History
44 lines (26 loc) · 1.26 KB

README.md

File metadata and controls

44 lines (26 loc) · 1.26 KB

mnist-cnn-tensorflow

"Convolutional Neural Network (CNN) for Handwritten Digit Recognition using TensorFlow and Keras. This code loads the MNIST dataset, preprocesses the images, builds a CNN model, and evaluates its performance. It also includes an example of making predictions on a custom test image."

Handwritten Digit Recognition with CNN

This repository contains Python code for a Convolutional Neural Network (CNN) designed to recognize handwritten digits. It uses the MNIST dataset for training and evaluation.

Contents

  • digit_recognition_cnn.py: Python script containing the code.
  • test_image.png: Example custom test image for prediction.

Getting Started

  1. Clone the repository.
  2. Run digit_recognition_cnn.py to train the model and make predictions.

Prerequisites

  • Python 3.x
  • TensorFlow
  • Keras
  • Matplotlib
  • PIL

Install the necessary packages using pip install -r requirements.txt.

Usage

  • Run digit_recognition_cnn.py to see the CNN in action.
  • To make predictions on your own images, replace test_image.png with your custom image.

Results

  • The model achieves an accuracy of XX% on the test set.

Acknowledgments

  • The code in this repository is based on a tutorial by [Link to Tutorial].

Author

  • Ganesh Adimalupu