pytorch-topological
pytorch-topological copied to clipboard
aidos-lab
A topological machine learning framework based on PyTorch
Just covering the basics for new users: suppose you don't care about topology _at all_, what's the smallest thing you can add to your code to make it 'topology-aware?'
- Some previous benchmarks by @crisbodnar: https://colab.research.google.com/drive/1CbLnKu4v964Gxb2FDsxp1kgPwe0pOKpl?usp=sharing - Suggestion for integration: use `str` parameter for `VietorisRipsComplex` - Add as optional dependency
Currently, the implementation of TOGL ignores the following features: - handling higher-order information properly - expanding simplicial complexes - making use of the dimension of features
Hi, I feel like there should be in-built functions for visualizing Persistence diagrams. Like now, I am using matplotlib, to scatter plot the `diagram` of `PersistenceInformation`, but it requires extra...
Import PersLayer to PyTorch topological. As apart of this effort, it would be nice to include the following deliverables: - PyTorch layer - Unit tests - Example of usage -...
Currently, there are no examples present for usage of TOGL. Would be good to provide example of use case.
As stated in the roadmap, currently, `guddhi` and `giotto-ph` are used for various purposes. We want to be able to allow the user to specify which backend to use, and...
Hi, Thanks for the great work and developing this library. I am trying to replicate the experiments from the Topological autoencoder paper using the script given as an example, but...
Hello, 1) I have used ripser and torch_topological libraries to compute cubical persistence of the same image but the two two diagrams are different. 2) About the wasserstein distance, I...
