Contrastive-Clustering icon indicating copy to clipboard operation
Contrastive-Clustering copied to clipboard

Published 20 hours ago • verified publisher icon Yunfan-Li

ImageNet 10

Open YIBO-0805 opened this issue 3 years ago • 3 comments

Hi，

I did not find a description about the distribution of the Imagenet-10 and the data-augment method you used in your paper and code. And I get a bad accuracy on this dataset.

I would like to know if you could describe in detail or if I get something wrong？

YIBO-0805 avatar Oct 18 '21 05:10 YIBO-0805

Hi, ImageNet-10 is a subset of ImageNet with 10 class indices provided in the dataset folder. The data augmentation for ImageNet-10 could be found at https://github.com/Yunfan-Li/Contrastive-Clustering/blob/dfda491ce22541265228e119d7e708fe752d4ad7/modules/transform.py#L21.

Yunfan-Li avatar Oct 18 '21 06:10 Yunfan-Li

Thank you for your reply. Following the dataset folder, I got 14,216 images. I would like to know how you screen out 13,000 images and how many images are in each category.

YIBO-0805 avatar Oct 18 '21 06:10 YIBO-0805

In our experiment, the training set of ImageNet is used with 1300 images in each class.

Yunfan-Li avatar Oct 18 '21 06:10 Yunfan-Li