kmeans_pytorch

kmeans_pytorch copied to clipboard

If selected is empty all data will become Nan

1

You don't handle the case when non of data is clustered into a cluster and if the num of cluster is big enough, all data will become nan.

Joshuaoneheart

Input of the same data leads to different results.

1

Hi, I tried to cluster the same data with Kmeans_pytorch, but got different clustering results. What is the cause of this? Looking forward to your reply.

zchwang

Hi! I wonder if I can use the function on multiple GPUs and if it works on DDP mode of PyTorch? Thanks!

Hugo-cell111

Error trying to cluster from numpy

1

Hi, I'm not really using pytorch, but I want to use balanced kmeans. My code is as follows: ``` from torch import from_numpy from balanced_kmeans import kmeans_equal ... # load...

carl-offerfit

Dear, When running the code, I also encountered the "center_shift=nan" bug (which was also reported in issue [#3](https://github.com/subhadarship/kmeans_pytorch/issues/3)). I would like to thank [@GenjiB](https://github.com/GenjiB) for identifying the issue: "If a...

yangnianzu0515

AsureDay

Please Share the requirement file requirements.txt file

hammad2008

IndexError: index_select(): Index is supposed to be a vector

1

This error occurs when I try to cluster with a set of tensors with n_clusters = 2.

Jayati-Kaushik

Hello, GPU-accelerated version of Kmeans, can pass in a tensor whose shape is 3 dimensional? For example, (3,758,32) is (batch,node,feature), and the batch is expected to be parallel.

280777510

TypeError: kmeans() got an unexpected keyword argument 'cluster_centers'

1

x_batch size is [100,256,3,3], len(x_batch) is 400,I want to use these datas to get the cluster is 100 of kmeans. When it is not the first time, I want to...

Beluooo-H