torchrecurrent.UnICORNNCell#
- class torchrecurrent.UnICORNNCell(input_size, hidden_size, bias=True, recurrent_bias=True, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, control_kernel_init=<function normal_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, dt=1.0, alpha=0.0, device=None, dtype=None)[source]#
An Undamped Independent Controlled Oscillatory RNN (UnICORNN) cell.
[arXiv]
The cell maintains two coupled state vectors, the hidden state \(\mathbf{h}(t)\) and the control state \(\mathbf{z}(t)\), which evolve according to
\[\begin{split}\begin{aligned} \mathbf{h}(t) &= \mathbf{h}(t-1) + \Delta t\,\hat{\sigma}(\mathbf{w}_{ch}) \circ \mathbf{z}(t), \\ \mathbf{z}(t) &= \mathbf{z}(t-1) - \Delta t\,\hat{\sigma}(\mathbf{w}_{ch}) \circ \Bigl[ \sigma\bigl( \mathbf{W}_{hh}\,\mathbf{h}(t-1) + \mathbf{W}_{ih}\,\mathbf{x}(t) + \mathbf{b}_{ih} \bigr) + \alpha\,\mathbf{h}(t-1) \Bigr], \end{aligned}\end{split}\]where \(\Delta t\) is the time step
dt
, and \(\alpha\) is the leakage constant.- Parameters:
input_size – The number of expected features in the input
x
.hidden_size – The number of features in the hidden state
h
.bias – If
False
, the layer does not use the input biasb_{ih}
. Default:True
.recurrent_bias – If
False
, the layer does not use the hidden biasb_{hh}
. Default:True
.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_()
.control_kernel_init – Initializer for
w_{ch}
. Default:torch.nn.init.normal_()
.bias_init – Initializer for
b_{ih}
. Default:torch.nn.init.zeros_()
.recurrent_bias_init – Initializer for
b_{hh}
. Default:torch.nn.init.zeros_()
.dt – Time step \(\Delta t\) between updates. Default:
1.0
.alpha – Leakage coefficient in the control update. Default:
0.0
.device – The desired device of parameters.
dtype – The desired floating point type of parameters.
- Inputs: input, (h, z)
input of shape
(batch, input_size)
or(input_size,)
: Tensor containing input features.h of shape
(batch, hidden_size)
or(hidden_size,)
: Previous hidden state.z of shape
(batch, hidden_size)
or(hidden_size,)
: Previous control state.
If (h, z) is not provided, both default to zeros.
- Outputs: (h_1, z_1)
h_1 of shape
(batch, hidden_size)
or(hidden_size,)
: Next hidden state.z_1 of shape
(batch, hidden_size)
or(hidden_size,)
: Next control 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 control weights, of shape
(hidden_size,)
.bias_ih – The learnable input bias, of shape
(hidden_size,)
.bias_hh – The learnable hidden bias, of shape
(hidden_size,)
.
Examples:
>>> cell = UnICORNNCell(10, 20, dt=0.5, alpha=0.1) >>> x = torch.randn(5, 3, 10) # (time_steps, batch, input_size) >>> h = torch.zeros(3, 20) # (batch, hidden_size) >>> z = torch.zeros(3, 20) # (batch, hidden_size) >>> outs_h, outs_z = [], [] >>> for t in range(x.size(0)): ... h, z = cell(x[t], (h, z)) ... outs_h.append(h) ... outs_z.append(z) >>> outs_h = torch.stack(outs_h, dim=0) >>> outs_z = torch.stack(outs_z, dim=0)
- __init__(input_size, hidden_size, bias=True, recurrent_bias=True, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function xavier_uniform_>, control_kernel_init=<function normal_>, bias_init=<function zeros_>, recurrent_bias_init=<function zeros_>, dt=1.0, alpha=0.0, 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
alpha
input_size
hidden_size
bias
recurrent_bias
training