deepxde.nn.jax

deepxde.nn.jax.fnn module

class deepxde.nn.jax.fnn.FNN(layer_sizes: ~typing.Any, activation: ~typing.Any, kernel_initializer: ~typing.Any, params: ~typing.Any = None, _input_transform: ~typing.Callable = None, _output_transform: ~typing.Callable = None, parent: ~typing.Type[~flax.linen.module.Module] | ~flax.core.scope.Scope | ~typing.Type[~flax.linen.module._Sentinel] | None = <flax.linen.module._Sentinel object>, name: str | None = None)

Bases: NN

Fully-connected neural network.

activation: Any

kernel_initializer: Any

layer_sizes: Any

name: str | None = None

params: Any = None

parent: Type[Module] | Scope | Type[_Sentinel] | None = None

scope: Scope | None = None

setup()

Initializes a Module lazily (similar to a lazy __init__).

setup is called once lazily on a module instance when a module is bound, immediately before any other methods like __call__ are invoked, or before a setup-defined attribute on self is accessed.

This can happen in three cases:

1. Immediately when invoking apply(), init() or init_and_output().

2. Once the module is given a name by being assigned to an attribute of another module inside the other module’s setup method (see __setattr__()):

   >>> class MyModule(nn.Module):
   ...   def setup(self):
   ...     submodule = nn.Conv(...)
   
   ...     # Accessing `submodule` attributes does not yet work here.
   
   ...     # The following line invokes `self.__setattr__`, which gives
   ...     # `submodule` the name "conv1".
   ...     self.conv1 = submodule
   
   ...     # Accessing `submodule` attributes or methods is now safe and
   ...     # either causes setup() to be called once.
   

3. Once a module is constructed inside a method wrapped with compact(), immediately before another method is called or setup defined attribute is accessed.

class deepxde.nn.jax.fnn.PFNN(layer_sizes: ~typing.Any, activation: ~typing.Any, kernel_initializer: ~typing.Any, params: ~typing.Any = None, _input_transform: ~typing.Callable = None, _output_transform: ~typing.Callable = None, parent: ~typing.Type[~flax.linen.module.Module] | ~flax.core.scope.Scope | ~typing.Type[~flax.linen.module._Sentinel] | None = <flax.linen.module._Sentinel object>, name: str | None = None)

Bases: NN

Parallel fully-connected network that uses independent sub-networks for each network output.

Parameters:

layer_sizes – A nested list that defines the architecture of the neural network (how the layers are connected). If layer_sizes[i] is an int, it represents one layer shared by all the outputs; if layer_sizes[i] is a list, it represents len(layer_sizes[i]) sub-layers, each of which is exclusively used by one output. Every layer_sizes[i] list must have the same length (= number of subnetworks). If the last element of layer_sizes is an int preceded by a list, it must be equal to the number of subnetworks: all subnetworks have an output size of 1 and are then concatenated. If the last element is a list, it specifies the output size for each subnetwork before concatenation.

activation: Any

kernel_initializer: Any

layer_sizes: Any

name: str | None = None

params: Any = None

parent: Type[Module] | Scope | Type[_Sentinel] | None = None

scope: Scope | None = None

setup()

Initializes a Module lazily (similar to a lazy __init__).

setup is called once lazily on a module instance when a module is bound, immediately before any other methods like __call__ are invoked, or before a setup-defined attribute on self is accessed.

This can happen in three cases:

1. Immediately when invoking apply(), init() or init_and_output().

2. Once the module is given a name by being assigned to an attribute of another module inside the other module’s setup method (see __setattr__()):

   >>> class MyModule(nn.Module):
   ...   def setup(self):
   ...     submodule = nn.Conv(...)
   
   ...     # Accessing `submodule` attributes does not yet work here.
   
   ...     # The following line invokes `self.__setattr__`, which gives
   ...     # `submodule` the name "conv1".
   ...     self.conv1 = submodule
   
   ...     # Accessing `submodule` attributes or methods is now safe and
   ...     # either causes setup() to be called once.
   

3. Once a module is constructed inside a method wrapped with compact(), immediately before another method is called or setup defined attribute is accessed.

deepxde.nn.jax.nn module

class deepxde.nn.jax.nn.NN(parent: ~typing.Type[~flax.linen.module.Module] | ~flax.core.scope.Scope | ~typing.Type[~flax.linen.module._Sentinel] | None = <flax.linen.module._Sentinel object>, name: str | None = None)

Bases: Module

Base class for all neural network modules.

apply_feature_transform(transform)

Compute the features by appling a transform to the network inputs, i.e., features = transform(inputs). Then, outputs = network(features).

apply_output_transform(transform)

Apply a transform to the network outputs, i.e., outputs = transform(inputs, outputs).

name: str | None = None

parent: Type[Module] | Scope | Type[_Sentinel] | None = None

scope: Scope | None = None