Domenico Muscillo

[CKA](https://arxiv.org/abs/1905.00414) and [CCA](https://arxiv.org/abs/1706.05806) similarities have been implemented by [jayroxis](https://github.com/jayroxis/CKA-similarity) and [moskomule](https://github.com/moskomule/anatome). However the second link is a library with other neural network representation similarities i am not sure it is...

I think it depends on the task. It may be used in some application to NAS or in some other model that could benefit from these similarities

Probably not. For [CKA](https://colab.research.google.com/github/google-research/google-research/blob/master/representation_similarity/Demo.ipynb) one uses the data matrix X (num_examples x num_features), computes a Gram matrix with it (in the link they either use linear or rbf kernels, but...

> Since this PR introduces some big breaking changes, I'm thinking it should be a part of the version 3 release. > > I'll create a v3.0 branch for that...

> ``` > import numpy as np > from pytorch_metric_learning.utils.accuracy_calculator import AccuracyCalculator > import umap > > if __name__ == '__main__': > umapper = umap.UMAP() > test_embeddings = np.random.normal(size=(100, 64))...