-
Notifications
You must be signed in to change notification settings - Fork 346
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
glossary #999
glossary #999
Conversation
Codecov Report
@@ 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
Continue to review full report at Codecov.
|
docs/user_guide/developer.rst
Outdated
.. tab:: TrainingPlan | ||
|
||
|
||
The training plan is a PyTorch Lightning Module that is initializd with a scvi-tools module object. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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. |
docs/user_guide/developer.rst
Outdated
It configures the optimizers, defines the training step and validation step, and computes metrics to be | ||
recorded during training. The training step and validation step are functions that take data, run it through | ||
the model and return the loss, which will then be used to optimize the model parameters in the Trainer. | ||
Overall, training plans can be used to develop complex inference schemes on top of modules. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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. |
docs/user_guide/developer.rst
Outdated
|
||
.. tab:: Model | ||
|
||
A model class is a user-facing object that contains the module as an attribute (i.e., ``self.module``). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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. |
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. | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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. | |
|
||
.. tab:: Module | ||
|
||
A module is the lower-level object that defines a generative model and inference scheme. A module will |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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 |
|
||
A module is the lower-level object that defines a generative model and inference scheme. A module will | ||
either inherit :class:`~scvi.module.base.BaseModuleClass` or :class:`~scvi.module.base.PyroBaseModuleClass`. | ||
Consequently, a module can either be implemented with PyTorch alone, or Pyro. In the PyTorch only case, the |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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 |
Co-authored-by: Galen Xing <[email protected]>
Fixes #995