torchrecurrent.MGUCell

class torchrecurrent.MGUCell(input_size, hidden_size, bias=True, activation_fn=<built-in method tanh of type object>, gate_activation_fn=<built-in method sigmoid of type object>, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, device=None, dtype=None)

A Minimal Gated Unit (MGU) cell.

This cell uses a single forget‐update gate to modulate both carry and candidate, reducing parameters relative to an LSTM:

\[\begin{split}\mathbf{f}(t) &= \sigma\bigl( \mathbf{W}_{ih}^{f}\,\mathbf{x}(t) + \mathbf{b}_{ih}^{f} + \mathbf{W}_{hh}^{f}\,\mathbf{h}(t-1) + \mathbf{b}_{hh}^{f} \bigr), \\[6pt] \tilde{\mathbf{h}}(t) &= \phi\bigl( \mathbf{W}_{ih}^{h}\,\mathbf{x}(t) + \mathbf{b}_{ih}^{h} + \mathbf{W}_{hh}^{h}\bigl(\mathbf{f}(t)\circ\mathbf{h}(t-1)\bigr) + \mathbf{b}_{hh}^{h} \bigr), \\[6pt] \mathbf{h}(t) &= \bigl(1 - \mathbf{f}(t)\bigr)\circ\mathbf{h}(t-1) \;+\;\mathbf{f}(t)\circ\tilde{\mathbf{h}}(t),\end{split}\]

where \(\circ\) is element‐wise product and \(\phi\) is a pointwise nonlinearity (default tanh).

Parameters:

input_size (int) – Number of features in the input \(\mathbf{x}(t)\).
hidden_size (int) – Number of features in the hidden state \(\mathbf{h}(t)\).
bias (bool, optional) – If False, disables both biases \(\mathbf{b}_{ih}\) and \(\mathbf{b}_{hh}\). Default: True.
activation_fn (Callable, optional) – Nonlinearity \(\phi\) for the candidate. Default: torch.tanh.
gate_activation_fn (Callable, optional) – Activation for the forget gate. Default: torch.sigmoid.
kernel_init (Callable, optional) – Initializer for input‐to‐hidden weights \(\mathbf{W}_{ih}^*\). Default: nn.init.xavier_uniform_.
recurrent_kernel_init (Callable, optional) – Initializer for hidden‐to‐hidden weights \(\mathbf{W}_{hh}^*\). Default: nn.init.xavier_uniform_.
bias_init (Callable, optional) – Initializer for input biases when bias=True. Default: nn.init.zeros_.
recurrent_bias_init (Callable, optional) – Initializer for hidden biases when bias=True. Default: nn.init.zeros_.
device (torch.device, optional) – Device of the parameters. Default: CPU.
dtype (torch.dtype, optional) – Data type of the parameters. Default: PyTorch float.

Inputs: input, hidden

input (Tensor): shape (H_in,) or (N, H_in), where H_in = input_size.
hidden (Tensor, optional): previous hidden state of shape
(H_out,) or (N, H_out), where H_out = hidden_size. Defaults to zero if not provided.

Outputs: h’

h’ (Tensor): next hidden state, same shape as hidden.

Shape:

input: \((N, H_{\mathrm{in}})\) or \((H_{\mathrm{in}})\).
hidden: \((N, H_{\mathrm{out}})\) or \((H_{\mathrm{out}})\).
output: \((N, H_{\mathrm{out}})\) or \((H_{\mathrm{out}})\).

weight_ih

input‐to‐hidden weights, shape (2*H, I), chunked into forget (f) and candidate (h) parts.

Type:: Tensor

weight_hh

hidden‐to‐hidden weights, shape (2*H, H), chunked into forget and candidate parts.

Type:: Tensor

bias_ih

input biases, shape (2*H,) if bias=True.

Type:: Tensor

bias_hh

hidden biases, shape (2*H,) if bias=True.

Type:: Tensor

Examples::

>>> cell = MGUCell(10, 20)
>>> x = torch.randn(5, 10)       # sequence length 5
>>> h0 = torch.zeros(20)         # initial hidden state
>>> hx = h0
>>> outs = []
>>> for t in range(x.size(0)):
...     hx = cell(x[t], hx)
...     outs.append(hx)

__init__(input_size, hidden_size, bias=True, activation_fn=<built-in method tanh of type object>, gate_activation_fn=<built-in method sigmoid of type object>, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, device=None, dtype=None)

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

Parameters:

input_size (int)
hidden_size (int)
bias (bool)
activation_fn (Callable)
gate_activation_fn (Callable)
device (device | None)
dtype (dtype | None)

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`
`bias_ih`
`bias_hh`
`training`