Using the MNIST dataset which consists of greyscale handwritten digits. It contains 70,000 images of handwritten digits: 60,000 for training and 10,000 for testing. Each image is 28x28 pixels. Building a basic neural network that can take one of these images and predict the digit in the image. I have used Pytorch to train the neural network. PyTorch is a very popular framework for deep learning. PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing.
geekquad / handwritten-digit-prediction Goto Github PK
View Code? Open in Web Editor NEWUsing the MNIST dataset which consists of greyscale handwritten digits. Each image is 28x28 pixels. Building and training a neural network that can take one of these images and predict the digit in the image.