osl_dynamics.inference.initializers#

Initializers for TensorFlow layers.

Attributes#

tfb

Classes#

`WeightInitializer`	Initialize weights to given value.
`RandomWeightInitializer`	Initialize weights to given value with random noise added.
`IdentityCholeskyInitializer`	Initialize weights to a flattened cholesky factor of identity matrices.
`NormalIdentityCholeskyInitializer`	Normal identity cholesky initializer.
`NormalCorrelationCholeskyInitializer`	Normal correlation cholesky initializer.
`NormalDiagonalInitializer`	Initializer for diagonal matrices with a normal error added.
`CopyTensorInitializer`	Initialize weights to another Tensor's value.

Functions#

`reinitialize_layer_weights`(layer)	Re-initializes the weights in a particular layer.
`reinitialize_model_weights`(model[, keep])	Re-initialize the weights in a model.

Module Contents#

osl_dynamics.inference.initializers.tfb[source]#

class osl_dynamics.inference.initializers.WeightInitializer(initial_value)[source]#

Bases: tensorflow.keras.initializers.Initializer

Initialize weights to given value.

Parameters:: initial_value (np.ndarray) – Value to initialise weights to. Note, the shape is not checked.

initial_value[source]#

class osl_dynamics.inference.initializers.RandomWeightInitializer(initial_value, std)[source]#

Bases: tensorflow.keras.initializers.Initializer

Initialize weights to given value with random noise added.

Parameters:

initial_value (np.ndarray) – Value to initialise weights to. Note, the shape is not checked.
std (float) – Standard deviation of the noise to add.

initial_value[source]#

std[source]#

class osl_dynamics.inference.initializers.IdentityCholeskyInitializer[source]#

Bases: tensorflow.keras.initializers.Initializer

Initialize weights to a flattened cholesky factor of identity matrices.

bijector[source]#

class osl_dynamics.inference.initializers.NormalIdentityCholeskyInitializer(std)[source]#

Bases: tensorflow.keras.initializers.Initializer

Normal identity cholesky initializer.

Initialize weights to a flattened cholesky factor of identity matrices with a normal error added to the diagonal.

Parameters:: std (float) – Standard deviation of the error to add.

std[source]#

bijector[source]#

class osl_dynamics.inference.initializers.NormalCorrelationCholeskyInitializer(std)[source]#

Bases: tensorflow.keras.initializers.Initializer

Normal correlation cholesky initializer.

Initialize weights to a flattened cholesky factor of correlation matrices with a normal error added to the flattened cholesky factor.

Parameters:

mean (float) – Mean of the error to add.
std (float) – Standard deviation of the error to add.

std[source]#

bijector[source]#

class osl_dynamics.inference.initializers.NormalDiagonalInitializer(std)[source]#

Bases: tensorflow.keras.initializers.Initializer

Initializer for diagonal matrices with a normal error added.

Parameters:: std (float) – Standard deviation of the error to add.

std[source]#

bijector[source]#

class osl_dynamics.inference.initializers.CopyTensorInitializer(tensor)[source]#

Bases: tensorflow.keras.initializers.Initializer

Initialize weights to another Tensor’s value.

Parameters:: tensor (tf.Tensor) – Tensor to copy.

tensor[source]#

osl_dynamics.inference.initializers.reinitialize_layer_weights(layer)[source]#

Re-initializes the weights in a particular layer.

Parameters:: layer (tf.keras.layers.Layer) – Layer to initialize weights for.
Return type:: None

Note

This function relies on each layer having an attribute for the initializer. Standard TensorFlow layers have this. You must specify a self.*_initializer attribute in any custom layer, otherwise this function will break.

osl_dynamics.inference.initializers.reinitialize_model_weights(model, keep=None)[source]#

Re-initialize the weights in a model.

Parameters:

model (tf.keras.Model) – Model to re-initialize weights for.
keep (list, optional) – List of str containing names for layers to not reinitialize.

Return type:

None