torchrecurrent.SCRNCell#

class torchrecurrent.SCRNCell(input_size, hidden_size, bias=True, recurrent_bias=True, context_bias=True, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, context_kernel_init=<function normal_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, context_bias_init=<function zeros_>, alpha=0.5, device=None, dtype=None)[source]#

A Structurally Constrained Recurrent Network (SCRN) cell.

[arXiv]

\[\begin{split}\begin{aligned} \mathbf{s}(t) &= (1 - \alpha)\,\bigl(\mathbf{W}_{ih}^{s}\,\mathbf{x}(t) + \mathbf{b}_{ih}^{s}\bigr) + \alpha\,\mathbf{s}(t-1), \\ \mathbf{h}(t) &= \sigma\Bigl( \mathbf{W}_{ch}^{h}\,\mathbf{s}(t) + \mathbf{b}_{ch}^{h} + \mathbf{W}_{ih}^{h}\,\mathbf{x}(t) + \mathbf{b}_{ih}^{h} + \mathbf{W}_{hh}^{h}\,\mathbf{h}(t-1) + \mathbf{b}_{hh}^{h} \Bigr), \\ \mathbf{y}(t) &= f\Bigl( \mathbf{W}_{ch}^{y}\,\mathbf{s}(t) + \mathbf{b}_{ch}^{y} + \mathbf{W}_{hh}^{y}\,\mathbf{h}(t) + \mathbf{b}_{hh}^{y} \Bigr) \end{aligned}\end{split}\]

where \(\sigma\) is the sigmoid activation and \(f\) is an optional output nonlinearity.

Parameters:

  • input_size – Number of input features

  • hidden_size – Number of hidden (and context) features

  • bias – If False, the layer does not use input-side bias b_ih. Default: True

  • recurrent_bias – If False, the layer does not use recurrent bias b_hh. Default: True

  • context_bias – If False, the layer does not use context bias b_ch. Default: True

  • kernel_init – Initializer for weight_ih. Default: torch.nn.init.xavier_uniform_()

  • recurrent_kernel_init – Initializer for weight_hh. Default: torch.nn.init.xavier_uniform_()

  • context_kernel_init – Initializer for weight_ch. Default: torch.nn.init.normal_()

  • bias_init – Initializer for bias_ih when bias=True. Default: torch.nn.init.zeros_()

  • recurrent_bias_init – Initializer for bias_hh when recurrent_bias=True. Default: torch.nn.init.zeros_()

  • context_bias_init – Initializer for bias_ch when context_bias=True. Default: torch.nn.init.zeros_()

  • alpha – Context interpolation parameter \(\alpha\). Default: 0.5

  • device – The desired device of parameters

  • dtype – The desired floating point type of parameters

Inputs: input, (h_0, s_0)

  • input of shape (batch, input_size) or (input_size,): tensor containing input features

  • h_0 of shape (batch, hidden_size) or (hidden_size,): initial hidden state

  • s_0 of shape (batch, hidden_size) or (hidden_size,): initial context state

If (h_0, s_0) is not provided, both default to zero.

Outputs: (h_1, s_1)

  • h_1 of shape (batch, hidden_size) or (hidden_size,): next hidden state

  • s_1 of shape (batch, hidden_size) or (hidden_size,): next context state

Variables:

  • weight_ih – input–hidden weights, of shape (2*hidden_size, input_size)

  • weight_hh – hidden–hidden weights, of shape (2*hidden_size, hidden_size)

  • weight_ch – context–hidden weights, of shape (2*hidden_size, hidden_size)

  • bias_ih – input biases, of shape (2*hidden_size) if bias=True

  • bias_hh – hidden biases, of shape (2*hidden_size) if recurrent_bias=True

  • bias_ch – context biases, of shape (2*hidden_size) if context_bias=True

  • alpha – learnable context interpolation scalar

Examples:

>>> cell = SCRNCell(10, 20, alpha=0.5)
>>> x = torch.randn(6, 3, 10)   # (time, batch, input_size)
>>> h = torch.zeros(3, 20)      # (batch, hidden_size)
>>> s = torch.zeros(3, 20)      # (batch, hidden_size) context
>>> hs = []
>>> for t in range(x.size(0)):
...     h, s = cell(x[t], (h, s))
...     hs.append(h)
>>> hs = torch.stack(hs, dim=0)  # (time, batch, hidden_size)
__init__(input_size, hidden_size, bias=True, recurrent_bias=True, context_bias=True, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, context_kernel_init=<function normal_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, context_bias_init=<function zeros_>, alpha=0.5, device=None, dtype=None)[source]#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__(input_size, hidden_size[, bias, ...])

Initialize internal Module state, shared by both nn.Module and ScriptModule.

add_module(name, module)

Add a child module to the current module.

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

buffers([recurse])

Return an iterator over module buffers.

children()

Return an iterator over immediate children modules.

compile(*args, **kwargs)

Compile this Module's forward using torch.compile().

cpu()

Move all model parameters and buffers to the CPU.

cuda([device])

Move all model parameters and buffers to the GPU.

double()

Casts all floating point parameters and buffers to double datatype.

eval()

Set the module in evaluation mode.

extra_repr()

Return the extra representation of the module.

float()

Casts all floating point parameters and buffers to float datatype.

forward(inp[, state])

Run one step of the recurrent cell.

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

get_extra_state()

Return any extra state to include in the module's state_dict.

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

half()

Casts all floating point parameters and buffers to half datatype.

init_weights()

ipu([device])

Move all model parameters and buffers to the IPU.

load_state_dict(state_dict[, strict, assign])

Copy parameters and buffers from state_dict into this module and its descendants.

modules()

Return an iterator over all modules in the network.

mtia([device])

Move all model parameters and buffers to the MTIA.

named_buffers([prefix, recurse, ...])

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

named_modules([memo, prefix, remove_duplicate])

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

named_parameters([prefix, recurse, ...])

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

parameters([recurse])

Return an iterator over module parameters.

register_backward_hook(hook)

Register a backward hook on the module.

register_buffer(name, tensor[, persistent])

Add a buffer to the module.

register_forward_hook(hook, *[, prepend, ...])

Register a forward hook on the module.

register_forward_pre_hook(hook, *[, ...])

Register a forward pre-hook on the module.

register_full_backward_hook(hook[, prepend])

Register a backward hook on the module.

register_full_backward_pre_hook(hook[, prepend])

Register a backward pre-hook on the module.

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module's load_state_dict() is called.

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module's load_state_dict() is called.

register_module(name, module)

Alias for add_module().

register_parameter(name, param)

Add a parameter to the module.

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

requires_grad_([requires_grad])

Change if autograd should record operations on parameters in this module.

set_extra_state(state)

Set extra state contained in the loaded state_dict.

set_submodule(target, module[, strict])

Set the submodule given by target if it exists, otherwise throw an error.

share_memory()

See torch.Tensor.share_memory_().

state_dict(*args[, destination, prefix, ...])

Return a dictionary containing references to the whole state of the module.

to(*args, **kwargs)

Move and/or cast the parameters and buffers.

to_empty(*, device[, recurse])

Move the parameters and buffers to the specified device without copying storage.

train([mode])

Set the module in training mode.

type(dst_type)

Casts all parameters and buffers to dst_type.

uses_double_state()

Return True if forward returns (h, c), else just h.

xpu([device])

Move all model parameters and buffers to the XPU.

zero_grad([set_to_none])

Reset gradients of all model parameters.

Attributes

T_destination

call_super_init

dump_patches

weight_ih

weight_hh

weight_ch

bias_ih

bias_hh

bias_ch

input_size

hidden_size

bias

recurrent_bias

training