Does someone reproduce the accuracy of imagenet1k?

[KeyKy]

Does someone reproduce the accuracy of imagenet1k?

[KeyKy]

the paper give the exp of imagenet1k however this repo seem to train in imagenet.

[endernewton]

For clarification, here ImageNet is ImageNet1K.

[KeyKy]

@endernewton Whether ImageNet1K is imagenet with 1000 classes or imagenet with 1000 training images? I found the paper[https://arxiv.org/pdf/2104.10972.pdf]: ImageNet-1K is a subset of the full ImageNet dataset [11], which consists of
14,197,122 images, divided into 21,841 classes. ImageNet-1K
was created by selecting a subset of 1.2M images from ImageNet-21K, that belong to 1000 mutually
exclusive classes.

[yuzhiguo07]

I have a very very basic question: which one is the ImageNet-1K on ImageNet's official website (https://image-net.org/download-images.php)? Since I only found the link of ImageNet21K and ILSVRC 2012-2017. I tried to download ILSVRC 2012, and the structure is a little bit difference with the Data preparation:

/path/to/imagenet/
  train/
    class1/
      img1.jpeg
    class2/
      img2.jpeg
  val/
    class1/
      img3.jpeg
    class2/
      img4.jpeg

in https://github.com/facebookresearch/deit/blob/main/README_deit.md. The train folder is correct, but the val folder is different: There is no class level folder.

  ILSVRC2012_img_val/
      img1.jpeg  
      img2.jpeg
      img3.jpeg

Sorry I'm a rookie in CV.