DEMOGEN - 756 trained deep models dataset
DEMOGEN
756 trained deep models dataset
Screenshots
 View Image |  View Image |
|---|---|
Hunter's comment
A codebase containing the code necessary to use the generalization dataset in "Predicting the Generalization Gap in Deep Networks with Margin Distributions" (ICLR 2019); the 756 trained deep models dataset, DEep MOdel GENeralization dataset (DEMOGEN), has training & test performance on the CIFAR-10 & CIFAR-100 datasets.
Link
https://github.com/google-research/google-research/tree/master/demogen
This is posted on Steemhunt - A place where you can dig products and earn STEEM.
View on Steemhunt.com
It is a 15.57 GB dataset. I'm not a machine learning engineer, but that should be a major help to anyone who is starting out in this field.