Skip to content

PierreBoyeau/autoeval

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

AutoEval reproducibility

This repository contains the code to reproduce the results of "AutoEval Done Right: Using Synthetic Data for Model Evaluation"

For this purpose, clone the repository. Next, download ImageNet, following instructions from here and place it in the data folder. The folder should contain the following files:

  • data/imagenet/raw_data/ILSVRC2012_devkit_t12.tar.gz
  • data/imagenet/raw_data/ILSVRC2012_img_val.tar

Then install snakemake (instructions here) and run the following command to reproduce the results:

snakemake --use-conda --cores 1

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages