torchrecurrent.tauGRU#

class torchrecurrent.tauGRU(input_size, hidden_size, num_layers=1, dropout=0.0, batch_first=False, delay=1, **kwargs)[source]#

Multi-layer tau-GRU neural network.

[arXiv]

Each layer consists of a tauGRUCell, which updates the hidden state with a weighted time-delay feedback term:

\[\begin{split}\begin{aligned} u_n &= \tanh(W_1 h_n + U_1 x_n), \\ z_n &= \tanh(W_2 h_{n-d} + U_2 x_n), \\ g_n &= \sigma(W_3 h_n + U_3 x_n), \\ a_n &= \sigma(W_4 h_n + U_4 x_n), \\ h_{n+1} &= (1 - g_n) \circ h_n + g_n \circ (u_n + a_n \circ z_n), \end{aligned}\end{split}\]

where \(d\) is the integer delay in recurrent steps. Delayed states before the beginning of the sequence are initialized to zero.

Parameters:

  • input_size – The number of expected features in the input x.

  • hidden_size – The number of features in the hidden state h.

  • num_layers – Number of recurrent layers. Default: 1

  • dropout – If non-zero, introduces a Dropout layer on the outputs of each layer except the last. Default: 0

  • batch_first – If True, input and output tensors are provided as (batch, seq, feature) instead of (seq, batch, feature). Default: False

  • delay – Integer delay \(d\) in recurrent steps. Default: 1

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

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

  • nonlinearity – Nonlinearity for \(u_n\) and \(z_n\). Default: torch.tanh()

  • gate_nonlinearity – Activation for \(g_n\) and \(a_n\). Default: torch.sigmoid()

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

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

  • bias_init – Initializer for input-side biases. Default: torch.nn.init.zeros_()

  • recurrent_bias_init – Initializer for recurrent biases. Default: torch.nn.init.zeros_()

  • device – The desired device of parameters.

  • dtype – The desired floating point type of parameters.

Inputs: input, h_0

  • input: tensor of shape \((L, H_{in})\) for unbatched input, \((L, N, H_{in})\) when batch_first=False or \((N, L, H_{in})\) when batch_first=True.

  • h_0: tensor of shape \((\text{num_layers}, H_{out})\) for unbatched input or \((\text{num_layers}, N, H_{out})\). Defaults to zeros if not provided.

Outputs: output, h_n

  • output: tensor containing the output features from the last layer, for each timestep.

  • h_n: tensor containing the final hidden state for each layer.

cells.{k}.weight_ih

input-hidden weights of shape (4*hidden_size, input_size) for k = 0, otherwise (4*hidden_size, hidden_size).

cells.{k}.weight_hh

hidden-hidden weights of shape (4*hidden_size, hidden_size).

cells.{k}.bias_ih

input-hidden biases of shape (4*hidden_size). Only present when bias=True.

cells.{k}.bias_hh

hidden-hidden biases of shape (4*hidden_size). Only present when recurrent_bias=True.

See also

tauGRUCell

__init__(input_size, hidden_size, num_layers=1, dropout=0.0, batch_first=False, delay=1, **kwargs)[source]#

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

Methods

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

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])

Define the computation performed at every call.

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.

initialize_cells(cell_class, **kwargs)

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([remove_duplicate])

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.

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

delay

input_size

hidden_size

num_layers

batch_first

dropout

cells

training