Training MNIST benchmark with PyTorch

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 for more details.

17 1 Apr. 6, 2022, 8:00 PM


Digital Object Identifier (DOI)

10.5281/zenodo.4344415 (2020-09-09T01:36UTC)

You cannot launch this artifact, as you do not have an active Chameleon allocation.

Download Archive

Download an archive containing the files of this artifact.