glossary

[adamgayoso]

Fixes #995

[codecov]

Codecov Report

Merging #999 (deabc31) into master (57c992a) will decrease coverage by 0.03%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master     #999      +/-   ##
==========================================
- Coverage   89.72%   89.69%   -0.04%     
==========================================
  Files          87       87              
  Lines        6182     6190       +8     
==========================================
+ Hits         5547     5552       +5     
- Misses        635      638       +3     

Impacted Files	Coverage Δ
scvi/_settings.py	87.91% <0.00%> (-2.45%)	⬇️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 57c992a...deabc31. Read the comment docs.

[galenxing]

Suggested change

	The training plan is a PyTorch Lightning Module that is initializd with a scvi-tools module object.
	The TrainingPlan is a PyTorchLightning Module that is initialized with a scvi-tools Module object.

[galenxing]

Suggested change

	Overall, training plans can be used to develop complex inference schemes on top of modules.
	Overall, child classes of TrainingPlan can be used to develop complex inference schemes on top of modules.

[galenxing]

Suggested change

	A model class is a user-facing object that contains the module as an attribute (i.e., ``self.module``).
	A Model class inherits :class:`~scvi.model.base.BaseModelClass` and is the user-facing object for interacting with a Module.

[galenxing]

Suggested change

	The model has a `train` method that learns the parameters of the module, and also contains methods
	for users to retrieve information from the module, like the latent representation of cells in a VAE.
	Conventionally, the post-inference model methods should not store data into the AnnData object, but
	instead return "standard" Python objects, like numpy arrays or pandas dataframes.
	The Model has a `train` method that learns the parameters of the Module, and also contains methods
	for users to retrieve information from the Module, like the latent representation of cells in a VAE.
	Conventionally, a Model's post-inference methods should not store data into the AnnData object, but
	instead return "standard" Python objects, like a numpy array or a pandas DataFrame.

[galenxing]

Suggested change

	A module is the lower-level object that defines a generative model and inference scheme. A module will
	A Module is the lower-level object that defines a generative model and inference scheme. A Module will

[galenxing]

Suggested change

	Consequently, a module can either be implemented with PyTorch alone, or Pyro. In the PyTorch only case, the
	Consequently, a Module can either be implemented with PyTorch alone, or Pyro. In the PyTorch only case, the