austin2905 / handwrittendigitrecognization

Ink-Digit_Scan

Welcome to Ink-Digit_Scan! This repository houses an neural network model designed for handwritten digit recognition. Our technology swiftly converts ink-based digit inputs into digital format.

My project builds a neural network to recognize handwritten digits. The dataset used in this article is the MNIST dataset, which contains 60,000 training images and 10,000 test images of handwritten digits.

The neural network used in this article is a simple feed-forward neural network with 3 hidden layers. The first hidden layer has 128 neurons, the second hidden layer has 64 neurons, and the third hidden layer has 32 neurons. The output layer has 10 neurons, one for each digit.

The neural network is trained using the backpropagation algorithm. The training process is divided into 10 epochs. In each epoch, the neural network is trained on the entire training dataset.

After the training process is complete, the neural network is evaluated on the test dataset. The neural network achieves an accuracy of 98.2% on the test dataset. This article explains how to build a neural network to recognize handwritten digits. The dataset used in this article is the MNIST dataset, which contains 60,000 training images and 10,000 test images of handwritten digits.

The neural network used in this article is a simple feed-forward neural network with 3 hidden layers. The first hidden layer has 128 neurons, the second hidden layer has 64 neurons, and the third hidden layer has 32 neurons. The output layer has 10 neurons, one for each digit.

The neural network is trained using the backpropagation algorithm. The training process is divided into 10 epochs. In each epoch, the neural network is trained on the entire training dataset.

After the training process is complete, the neural network is evaluated on the test dataset. The neural network achieves an accuracy of 98.2% on the test dataset.

DIRECTIONS OF USE:

1. Clone the repository

2. Open the terminal and move to the cloned directory

3. type the command "pip install -r requirements.txt"

4. Then type "Python main.py"

5. then after the model is trained, type "Python GUI.py" for using it.

6. To improve the model or change the hyperparameters to increase the accuracy, make changes in the file "Model.py"

7. NOTE:

8. Install tensorflow gpu for training the model efficiently. to know how to install tensorflow gpu, refer the official page of tensorflow and follow their instructions under pip category with respect to your requirements.