ZhiyuanDang

Thanks for your reply. I have checked these corresponding issues #49 before I propose this issue. It is weird that the training and test k-means results on CIFAR-10/20 are fine,...

For the same evaluation method (from #49 ), CIFAR-10/20 and STL-10 can achieve the same train and test ACC. However, ImageNet-50 still obtain 65% training ACC and 38% test ACC....

Hi @wvangansbeke , Thanks for your reply, Could you please release the k-mean code for reference?

你好，图4的混淆矩阵是通过eval.py的第86-88行的实现的，有参数可以选择混淆矩阵的保存位置。 至于图5，同样是在eval.py，我们可以获得每类的前多个原型，然后我按照他们的预测类标，手动将他们拼齐为一类并手动标注相似的真实标签。

Hi @miziha-zp , Have you solved your PyTorch version issue? I will rerun the code to reproduce the results (At now, in Epoch 9/100, we get 0.81 ACC in CIFAR-10)....

My first epoch result is 0.5689 higher than your results 0.4981. Maybe something wrong in `simclr.py`, I consider uploading the model and took neighbors to fix this issue. Or could...

No, I always use the pre-trained model from SCAN. The output log is the same as mine. Therefore, the `simclr.py` I uploaded is correct. Since I run the code in...

f是embedding features, p是clustering assignment. 也就是说，通过Features来寻找最近邻样本的Index，然后用到p上。

Ok, I will upload the well-trained models ASAP.

Hi, first, you should create a pre-train config file same as files in configs/pretext. Then, you train a pre-train model using this file. After that, you follow the usages section...