scvi-tools
scvi-tools copied to clipboard
Deep probabilistic analysis of single-cell and spatial omics data
Good day, I am trying to update a model I created with an older version of scvi `scvi.model.SCVI.convert_legacy_save('./results/reference_signatures/', './results/eference_signatures_updated/')` but get the error below: ``` --------------------------------------------------------------------------- KeyError Traceback (most recent...
**Is your feature request related to a problem? Please describe.** I am trying to run a procedure called self projection with a scANVI model. The procedure entails taking a trained...
The following `encode` function used to be in the `jvae.py` in scvi-tools version 0.8.0 is missing in the current scvi.external.GIMVI module: ```python def encode( self, x: torch.Tensor, mode: int )...
When using pytest fixtures to create simple SCVI models in test_model, the runtime of the suite increases from 4 -> 14 seconds, as reported in #1576
Support for NumPyro as detailed in https://github.com/scverse/scvi-tools/issues/1366. https://github.com/scverse/scvi-tools/pull/1495 can be used as a starting point.
The jax backend currently has a very simple device management option. We would like to improve it such that users can specify specific devices to run on like with our...
Addressing comment here https://github.com/scverse/scvi-tools/blob/master/scvi/module/base/_jax_module_wrapper.py#L23
First reported in https://discourse.scverse.org/t/totalvi-nan-loss-with-few-proteins/45/3, this bug was recently reproduced in a dataset with 300 proteins. The cause of the issue is unknown, but setting `empirical_protein_background_prior=False` results in proper training. Associated...
Reimplementation of PeakVI in Jax. This is meant to both see if we can get a similar speed up in PeakVI, as well as understanding the limitations of the `JaxModuleWrapper`...