Digit Recognizer using Neural Networks

Digit Recognizer using Neural Networks is a machine learning project that employs neural network models to recognize hand-written digits. It's a common task in computer vision and deep learning, often used as an introductory example for image classification.

Introduction

Recognizing hand-written digits is a fundamental problem in computer vision and machine learning. This project focuses on implementing and training neural network models to accurately identify digits (0-9) from images of handwritten numbers.

Features

• Implementation of neural network architectures using popular frameworks like TensorFlow or PyTorch.
• Training and evaluation of models with various hyperparameters.
• Visualization of training and validation results.
• Custom digit recognition using trained models.

Using Gradio for Digit Recognition

With the Gradio interface integrated into this project, you can draw a digit on a sketchpad, and the trained neural network model will interpret and recognize the digit. This interactive feature allows you to quickly test the model's accuracy and see how well it performs on your own handwritten digits.

Steps for Running the trained model

• Open the following .pynb file in google colab.
• Run the Notebook
• At the end you will find SketchPad for drawing the digits and the model will recognize it.