Mathieu Carrière

perslay

5

A pull request for adding the PersLay Tensorflow model in the representations module

Mapper + GIC wrapper

9

A pull request for adding a Python class that can compute both Mapper and GIC complexes

Better documentation for persistence representations

1

Discussing with Wojciech made me realize that the doc is not sufficiently explicit w.r.t. the approximations we do when computing some vectorizations (such as persistence images).

In the current module, sliced wasserstein has two versions, depending on whether you want to compute SW on a pair of PDs, or to generate a pairwise matrix from a...

ToMATo notebook

1

I think it could be nice to have a notebook on ToMATo (so that all examples are in one place). Maybe we can just copy-paste Marc's code in a notebook:...

The current layer for computing persistence diagrams on simplex trees in TensorFlow, `LowerStarSimplexTreeLayer`, only works for lower-star filtrations. It would nice to provide a `SimplexTreeLayer` that takes filtration values on...

Exact version of sliced wasserstein distance, as the current version is bugged

[ToMATo] relate PD points to clusters

1

It would be nice to have a way to relate the points of the persistence diagram to the corresponding clusters, something like `tomato.labels_[i]` corresponds to persistence diagram point `i`. I...