Contrastive-Clustering

Contrastive-Clustering copied to clipboard

Cluster-level和instance-level

4

您好，paper原文中提到将表征解耦成instance-level和cluster-level，可以取得更好的效果。请问如何理解instance-level和cluster-level之间的关系呢，这两者是independent的吗？ 

myt517

Imbalanced Dataset

1

Hi, Thank you for this implementation. It is my understanding that some contrastive frameworks build upon entropy maximization, which leads to inapplicability in the contexts of imbalanced datasets. From the...

millanp95

ImageNet 10

3

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...

YIBO-0805

some question about softmax’s output

1

大佬，应该是中国人吧，我就用中文了： 是这样，我用自己的数据训练了一下，然后前向推理时，我在softmax那个地方加了个日志，把输出写到本地看了一下，排序后发现最大的输出并不是“赢者通吃”的状态，甚至出现了有并列最大值的情况，这种状况下，使用argmax获得到的索引能直接作为类别使用么？ 可能是我的使用方式不当，希望大佬指点一下； 优秀的工作，感谢分享！

Allfu

t-SNE plotting utils

3

Hey, Thanks for sharing the code and writing such a good paper! Can you give me some more info on how I can use your code to generate the t-SNE...

sramakrishnan247

Computational requirements for Training

4

Hey, Can I train this on Google colab? How long will it take in general? Can you share some more info on where i can run this code?

sramakrishnan247

Imagenet-10

3

Thanks for sharing information about how to use different datasets. How can I use the datasets info to download Imagenet-10? Do I need to download the entire Imagenet dataset and...

sramakrishnan247

New dataset format

7

Hello, I'd like to train this model on new image datasets. so what should be the file structure for the input dataset? As it is an unsupervised classification, so will...

Aditya-shahh

关于代码的运行

8

你好，我想问下，我用的是window的系统，用pycharm运行train.py，只出现Files already downloaded and verified Files already downloaded and verified，请问这是怎么回事呢？我想跑几个数据集和你的方法做对比实验，请问你可以提供一些帮助吗？

zhangyuanyang21

关于baseline的疑问

2

您好，请问一下，在baseline的对比中。K-means的特征向量是如何得到的呢？ 

oYoungCo