HandWritten numbers recognition

HandWritten numbers recognition. This project was made to learn how to use neural networks in Python. The goal was to recognize handwritten numbers from 0 to 9. The dataset used is the MNIST dataset, which is a large database of handwritten digits that is commonly used for training various image processing systems. The neural network was made using the Pytorch library.
I used Google Colab to run the code and train the neural network that was composed of 3 layers. The first layer has 784 neurons, the second layer has 128 neurons, and the last layer has 10 neurons. The neural network was trained for 10 epochs with a batch size of 64. The accuracy of the neural network was around 98% on the test dataset.