Training and testing done in Python, recognition web done in JavaScript.
Webapp to recognize handwritten digits using mnist model.
MNIST tutorial in browser using Tensorflow.js
BlockBuild is an educational and experimental platform for visually constructing neural networks through block-based programming. Users can build networks by connecting functional blocks, adjust hyperparameters such as the number of epochs, learning rate, and noise level, and train models on standard or custom datasets, including MNIST.
A simple feed forward neural network implementation for predicting handwritten digits.
Converts idx files into Javascript objects. Can be used to import the MNIST dataset files directly from javascript.
An implementation showcasing the deployment of machine learning model onto the flask server with live demo deployed on AWS Lambda.
Add a description, image, and links to the mnist-dataset topic page so that developers can more easily learn about it.
To associate your repository with the mnist-dataset topic, visit your repo's landing page and select "manage topics."