Guanhua Feng

Over clusters

4

嗨，跑了infomap在part1_test结果, 但是聚类结果类别数是19276 但是真实类别是8573类。为啥会有这么大的类别差异呢

Question about CPU out of memory

10

Hi, I run the experiments with my own dataset, which the number of training samples is about 1000 and the number of testing samples is about 1500. but in the...

Hi, thanks for your great work. I changed the HEADS CLS_LAYER: Linear to arcface or circle, but got the following error: raise TypeError("Input labels type is not a torch.Tensor. Got...

Code on computing the anomaly score is inconsistent with the paper

3

Hi, Thanks for your work. From formula(6) in paper:  for formula (7) in paper, it should be:  ### **### "**with N_b (m^* ) the b nearest patch-features in...

It will be more convenient for you to use torch.einsum for tensor dimension transormation.