torchrecurrent.coRNNCell#
- class torchrecurrent.coRNNCell(input_size, hidden_size, bias=True, recurrent_bias=True, cell_bias=True, dt=1.0, gamma=0.0, epsilon=0.0, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, cell_kernel_init=<function xavier_uniform_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, cell_bias_init=<function zeros_>, device=None, dtype=None)[source]#
A Coupled Oscillatory RNN cell.
[arXiv]
\[\begin{split}\begin{aligned} \mathbf{c}(t) &= \mathbf{c}(t-1) + \Delta t \,\tanh\Bigl( \mathbf{W}_{ih}\mathbf{x}(t) + \mathbf{b}_{ih} + \mathbf{W}_{hh}\mathbf{h}(t-1) + \mathbf{b}_{hh} + \mathbf{W}_{ch}\mathbf{c}(t-1) + \mathbf{b}_{ch} \Bigr) - \Delta t\,\gamma\,\mathbf{h}(t-1) - \Delta t\,\epsilon\,\mathbf{c}(t), \\ \mathbf{h}(t) &= \mathbf{h}(t-1) + \Delta t\,\mathbf{c}(t) \end{aligned}\end{split}\]where \(\Delta t\) (
dt) is the integration step size, \(\gamma\) damps the hidden state, and \(\epsilon\) damps the cell state.- Parameters:
input_size – The number of expected features in the input
x.hidden_size – The number of features in the states
handc.bias – If
False, the layer does not use input-side biasb_ih. Default:True.recurrent_bias – If
False, the layer does not use recurrent biasb_hh. Default:True.cell_bias – If
False, the layer does not use cell biasb_ch. Default:True.dt – Integration step size \(\Delta t\). Default:
1.0.gamma – Damping on hidden-state term. Default:
0.0.epsilon – Damping on cell-state term. Default:
0.0.kernel_init – Initializer for
W_{ih}. Default:torch.nn.init.xavier_uniform_().recurrent_kernel_init – Initializer for
W_{hh}. Default:torch.nn.init.xavier_uniform_().cell_kernel_init – Initializer for
W_{ch}. Default:torch.nn.init.xavier_uniform_().bias_init – Initializer for
b_{ih}whenbias=True. Default:torch.nn.init.zeros_().recurrent_bias_init – Initializer for
b_{hh}whenrecurrent_bias=True. Default:torch.nn.init.zeros_().cell_bias_init – Initializer for
b_{ch}whencell_bias=True. Default:torch.nn.init.zeros_().device – The desired device of parameters.
dtype – The desired floating point type of parameters.
- Inputs: input, (h_0, c_0)
input of shape
(batch, input_size)or(input_size,): Tensor containing input features.h_0 of shape
(batch, hidden_size)or(hidden_size,): Tensor containing the initial hidden state.c_0 of shape
(batch, hidden_size)or(hidden_size,): Tensor containing the initial cell state.
If
(h_0, c_0)is not provided, both default to zeros.- Outputs: (h_1, c_1)
h_1 of shape
(batch, hidden_size)or(hidden_size,): Tensor containing the next hidden state.c_1 of shape
(batch, hidden_size)or(hidden_size,): Tensor containing the next cell state.
- Variables:
weight_ih – The learnable input–hidden weights, of shape
(hidden_size, input_size).weight_hh – The learnable hidden–hidden weights, of shape
(hidden_size, hidden_size).weight_ch – The learnable cell–hidden weights, of shape
(hidden_size, hidden_size).bias_ih – The learnable input–hidden bias, of shape
(hidden_size).bias_hh – The learnable hidden–hidden bias, of shape
(hidden_size).bias_ch – The learnable cell–hidden bias, of shape
(hidden_size).
Note
The cell and hidden states interact like a second‐order oscillator, supporting rich, stable dynamics over long horizons.
Examples:
>>> cell = coRNNCell(10, 20, dt=0.5, gamma=0.1, epsilon=0.05) >>> x = torch.randn(5, 3, 10) # (time_steps, batch, input_size) >>> h, c = torch.zeros(3, 20), torch.zeros(3, 20) >>> out_h = [] >>> for t in range(x.size(0)): ... h, c = cell(x[t], (h, c)) ... out_h.append(h) >>> out_h = torch.stack(out_h, dim=0) # (time_steps, batch, hidden_size)
- __init__(input_size, hidden_size, bias=True, recurrent_bias=True, cell_bias=True, dt=1.0, gamma=0.0, epsilon=0.0, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, cell_kernel_init=<function xavier_uniform_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, cell_bias_init=<function zeros_>, 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
fnrecursively to every submodule (as returned by.children()) as well as self.bfloat16()Casts all floating point parameters and buffers to
bfloat16datatype.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
doubledatatype.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
floatdatatype.forward(inp[, state])Run one step of the recurrent cell.
get_buffer(target)Return the buffer given by
targetif 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
targetif it exists, otherwise throw an error.get_submodule(target)Return the submodule given by
targetif it exists, otherwise throw an error.half()Casts all floating point parameters and buffers to
halfdatatype.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_dictinto 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
targetif 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_destinationcall_super_initdump_patchesweight_ihweight_hhweight_chbias_ihbias_hhbias_chinput_sizehidden_sizebiasrecurrent_biastraining