Giovanni Palla
Giovanni Palla
hi @Chengwei94 , can you report what are the rest of the parameters for the prepare and solve method?
hi @Chengwei94 sorry for late reply, yes the Euclidean cost is expected to take more memory than the squared euclidean. All the costs except the squared euclidean are less memory...
- try increase the taus for the failing tests for FGW/GW problems - default to None the n iterations
ok then i think we need to raise this to @michalk8 because it is not expected
missing: - [x] hyperparameters section - [x] fill the table of the problems
yes lets deprecate!
Hi @katelynxli , thanks a lot for your interest in moscot! > This has been running now for over 2.5 days, so it is extremely slow. I am wondering if...
hi @Marius1311 ! I think #559 is related and there are some possible solutions, let us know if it works!
Just saw this, really cool! Especially for spatial plots this is very useful. Seurat already supports a basic functionality like the one you show https://satijalab.org/seurat/v3.1/spatial_vignette.html
hi @sokratiag , thanks for the question, unfortunately not yet but we plan to have a draft for it soon, following #407