Skip to content

v1.0 - Code corresponding to NeurIPS'21 Datasets and Benchmarks version of the whitepaper

Compare
Choose a tag to compare
@max-andr max-andr released this 29 Nov 14:10
· 203 commits to master since this release
d3795a0

Updates:

  • New ImageNet leaderboards (Linf and common corruption) and relevant benchmarking functions (including ImageNet evaluation on a fixed subset of 10% of the test set).
  • New models and leaderboard entries (now in total: 120+ evaluations, 80+ models).