p2pfl.learning.frameworks.tensorflow.keras_model module

Keras model abstraction for P2PFL.

class p2pfl.learning.frameworks.tensorflow.keras_model.KerasModel(model, params=None, num_samples=None, contributors=None, additional_info=None, compression=None)

Bases: P2PFLModel

P2PFL model abstraction for TensorFlow/Keras.

Parameters:

• model (Model) – The Keras model to encapsulate.

• params (list[ndarray] | bytes | None) – Optional initial parameters (list of NumPy arrays or bytes).

• num_samples (int | None) – Optional number of samples used for training.

• contributors (list[str] | None) – Optional list of contributor nodes.

• additional_info (dict[str, Any] | None) – Optional dictionary for extra information.

• compression (dict[str, dict[str, Any]] | None) – Optional dictionary for compression settings.

get_framework()

Retrieve the model framework name.

Return type:

str

Returns:

The name of the model framework.

get_parameters()

Get the parameters of the model.

Return type:

list[ndarray]

Returns:

The parameters of the model

set_parameters(params)

Set the parameters of the model.

Parameters:

params (list[ndarray] | bytes) – The parameters of the model.

Raises:

ModelNotMatchingError – If parameters don’t match the model.

Return type:

None

exception p2pfl.learning.frameworks.tensorflow.keras_model.ModelNotBuiltError

Bases: Exception

Raised when a model is not built.