sciml.parameters¶

The nominal values and the fit parameters of a network.

A problem describes the elements of a network in groups: an entry is given for the network (net1), for a layer (net1.layer1) or for an array (net1.layer1.weight), and the more specific entry wins. This is how a problem sets the elements of one layer to 0.0 while the other layers keep the values of the array file, and how it estimates one layer and freezes the others.

covered_arrays ¶

covered_arrays(network, key)

Get the arrays an entry covers.

Parameters:

Name	Type	Description	Default
`network`	`Network`	the network.	required
`key`	`str`	the network (`net1`), a layer (`net1.layer1`) or an array (`net1.layer1.weight`).	required

Returns:

Type	Description
`int`	How specific the entry is (0 for the network, 1 for a layer, 2 for an
`list[tuple[str, str]]`	array) and the arrays as pairs of layer id and array name. Only the
`tuple[int, list[tuple[str, str]]]`	arrays which are parameters are covered, i.e. not the running
`tuple[int, list[tuple[str, str]]]`	statistics of a normalization layer.

Raises:

Type	Description
`NetworkImportError`	if the key does not name the network, one of its layers or one of their arrays.

resolve_entries ¶

resolve_entries(network, entries)

Resolve the entries of a problem to the arrays of a network.

Parameters:

Name	Type	Description	Default
`network`	`Network`	the network.	required
`entries`	`Mapping[str, T]`	key of the entry -> value, see `covered_arrays`.	required

Returns:

Type	Description
`dict[tuple[str, str], T]`	layer id and array name -> the value of the most specific entry which
`dict[tuple[str, str], T]`	covers the array. An array no entry covers is not part of it.

Raises:

Type	Description
`NetworkImportError`	if a key does not name the network, a layer or an array.

nominal_parameters ¶

nominal_parameters(network, values=None)

Get the nominal values of the arrays of a network.

Parameters:

Name	Type	Description	Default
`network`	`Network`	the network with the values of its array file.	required
`values`	`Mapping[str, float] \| None`	key of the entry -> value of every element the entry covers, see `covered_arrays`. An array no entry covers keeps the values of the array file.	`None`

Returns:

Type	Description
`NetworkParameters`	The arrays in the PyTorch layout. The network is not changed.

Raises:

Type	Description
`NetworkImportError`	if a key does not name the network, a layer or an array, if a value is not finite, or if an array of a layer of the forward pass has values neither in the array file nor in `values`.

network_fit_parameters ¶

network_fit_parameters(
    network, estimate, bounds, external=False
)

Create the fit parameters of the estimated elements of a network.

estimate and bounds are given for the network, for a layer or for an array, and the more specific entry wins, see covered_arrays.

The nominal values of the elements are the values the network carries, which are the start values of the estimated elements and the values of the frozen ones. They are set on the network, not here, so that the network a hybridization runs is the network the fit parameters describe: dataclasses.replace(network, parameters=nominal_parameters(network, values)).

The elements of a layer which the forward pass does not call are left out: the outputs of the network do not depend on them, so a fit cannot estimate them.

Parameters:

Name	Type	Description	Default
`network`	`Network`	the network with the nominal values of its elements.	required
`estimate`	`Mapping[str, bool]`	key of the entry -> whether the elements are estimated. An element no entry covers is not estimated.	required
`bounds`	`Mapping[str, tuple[float, float]]`	key of the entry -> lower and upper bound of the elements. An estimated element no entry covers is not bounded.	required
`external`	`bool`	whether the elements are not entities of a model, which is the case for a network which runs before the simulation. The target of such a parameter is `sciml:<id>`. The elements of a network which is compiled into a model are entities of it.	`False`

Returns:

Type	Description
`list[FitParameter]`	One parameter per estimated element, named by the id of the element,
`list[FitParameter]`	with the nominal value as start value, the linear scale and the unit
`list[FitParameter]`	`dimensionless`, in the order of `Network.parameter_ids`.

Raises:

Type	Description
`NetworkImportError`	if a key does not name the network, a layer or an array, or if an estimated element has no nominal value.
`ValueError`	if a nominal value is outside of its bounds.