[model]

Model interfacing submodule, defining an API an derived applications.

This declearn submodule provides with:

• Model and Vector abstractions, used as an API to design FL algorithms.
• Submodules implementing interfaces to various frameworks and models.

Default Submodules

The automatically-imported submodules implemented here are:

• api: Model and Vector abstractions' defining module.
  • Model: abstract API to interface framework-specific models.
  • Vector: abstract API for data tensors containers.
• sklearn: Scikit-Learn based or oriented tools
  • NumpyVector Vector for numpy array data structures.
  • SklearnSGDModel Model for scikit-learn's SGDClassifier and SGDRegressor.

Optional Submodules

The optional-dependency-based submodules that may be manually imported are:

• haiku: Jax- and Haiku-interfacing tools.
  • HaikuModel: Model to wrap a haiku-transformable model function.
  • JaxNumpyVector: Vector for jax array data structures.
• tensorflow: TensorFlow-interfacing tools
  • TensorflowModel: Model to wrap any tensorflow-keras Layer model.
  • TensorflowOptiModule: Hacky OptiModule to wrap a keras Optimizer.
  • TensorflowVector: Vector for tensorflow Tensor and IndexedSlices.
• torch: PyTorch-interfacing tools
  • TorchModel: Model to wrap any torch Module model.
  • TorchOptiModule: Hacky OptiModule to wrap a torch Optimizer.
  • TorchVector: Vector for torch Tensor objects.