This notebook reproduces a simple benchmark experiment that trains a convolutional neural network based on the MNIST dataset. In particular, the neural network is built and trained with PyTorch.
MNIST is a database with 60,000 training images and 10,000 testing images that contains hand-written digits. Please see http://yann.lecun.com/exdb/mnist/ for more details.
Digital Object Identifier (DOI)10.5281/zenodo.4344414
Launching this artifact will open it within Chameleon’s shared Jupyter experiment environment, which is accessible to all Chameleon users with an active allocation.