Contrastive-Clustering issues

Low Accuracy and NMI

3

Hi, Thank you for sharing your code. I would like to reproduce your results on CIFAR-10, I ran your original code with 4 GPUs and the results are attached below....

mrsadeghi95-preteckt

loss和论文里好像不太一样啊

13

是这样的论文里的loss是很简单的ne xent loss但我看您的代码好像是又进行了简化还是有什么改变

11411511

About the dataset concatenation

1

Excellent work! We are grateful that the codes can be released for study. I have a question about the creation of the dataset: dataset = data.ConcatDataset([train_dataset, test_dataset]) I guess here...

yuanhaoguo

CIFAR-10数据集下acc较低

8

![DD1B6B6D-E90F-47F1-A804-D22CC5531CC8](https://user-images.githubusercontent.com/48206866/157261651-45829f73-bc3e-42cf-af55-c815216e1584.jpeg) 大佬我想问问这样的运行结果算是正常的吗，如果不是的话可能是哪里有问题呀😣

Yvein

weight_decay

5

Why the parameter 'weight_decay' set in code is 0.

YIBO-0805

About loss backward and parameter update

4

作者您好，感谢您这出色的工作。对于损失函数的传播和projector的参数更新我存在一点疑问：您的网络中并列存在instance_projector和cluster_projector，同时两个projector在正向传播过程中各自产生一个loss，您的做法是将两个projector的loss相加后再进行loss.backward()，这样的做法可以通过梯度下降同时优化两个并列的projector吗？这种方式和分别依次进行不同projector的loss.backward()有什么不同吗？谢谢。

skr998