torchrecurrent.FastGRNN#
- class torchrecurrent.FastGRNN(input_size, hidden_size, num_layers=1, dropout=0.0, batch_first=False, **kwargs)[source]#
Multi-layer FastGRNN.
[arXiv]
Each layer is a
FastGRNNCell
, a gated recurrent unit with two scalar parameters \(\zeta\) and \(\nu\) controlling the tradeoff between the candidate state and the previous hidden state:\[\begin{split}\begin{aligned} z(t) &= \sigma(W_{ih} x(t) + b_{ih}^z + W_{hh} h(t-1) + b_{hh}^z), \\ \tilde{h}(t) &= \tanh(W_{ih} x(t) + b_{ih}^h + W_{hh} h(t-1) + b_{hh}^h), \\ h(t) &= \bigl[\sigma(\zeta) (1 - z(t)) + \sigma(\nu)\bigr] \circ \tilde{h}(t) + z(t) \circ h(t-1), \end{aligned}\end{split}\]where \(\sigma\) is the sigmoid and \(\circ\) is elementwise multiplication.
- Parameters:
input_size – Number of expected features in the input x.
hidden_size – Number of features in the hidden state.
num_layers – Number of stacked recurrent layers. Default: 1
dropout – If non-zero, applies dropout after each layer (except last). Default: 0
batch_first – If
True
, inputs/outputs are shaped (batch, seq, feature) instead of (seq, batch, feature). Default: Falsebias – If
False
, disables input biases. Default: Truerecurrent_bias – If
False
, disables recurrent biases. Default: Truenonlinearity – Activation for the gate \(z\). Default:
torch.sigmoid()
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_()
bias_init – Initializer for b_{ih}. Default:
torch.nn.init.zeros_()
recurrent_bias_init – Initializer for b_{hh}. Default:
torch.nn.init.zeros_()
zeta_init – Initial value for scalar \(\zeta\). Default: 3.0
nu_init – Initial value for scalar \(\nu\). Default: -3.0
device – Desired device of parameters.
dtype – 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) whenbatch_first=True
.h_0: tensor of shape (num_layers, H_out) for unbatched input, or (num_layers, N, H_out) when batched. Defaults to zeros.
Where:
\[\begin{split}\begin{aligned} N &= \text{batch size} \\ L &= \text{sequence length} \\ H_{in} &= \text{input size} \\ H_{out} &= \text{hidden size} \end{aligned}\end{split}\]- Outputs: output, h_n
output: tensor of shape (L, H_out) for unbatched input, (L, N, H_out) when
batch_first=False
, or (N, L, H_out) whenbatch_first=True
, containing hidden states from the last layer.h_n: tensor of shape (num_layers, H_out) (unbatched) or (num_layers, N, H_out) with the final hidden state.
- cells.{k}.weight_ih
input–hidden weights of the \(k\)-th layer, shape (hidden_size, input_size) for k=0, otherwise (hidden_size, hidden_size).
- cells.{k}.weight_hh
hidden–hidden weights of the \(k\)-th layer, shape (hidden_size, hidden_size).
- cells.{k}.bias_ih
input biases of the \(k\)-th layer, shape (2*hidden_size,) if
bias=True
.
- cells.{k}.bias_hh
hidden biases of the \(k\)-th layer, shape (2*hidden_size,) if
recurrent_bias=True
.
- cells.{k}.zeta
scalar parameter \(\zeta\), shape (1,).
- cells.{k}.nu
scalar parameter \(\nu\), shape (1,).
See also
Examples:
>>> rnn = FastGRNN(10, 20, num_layers=2) >>> x = torch.randn(5, 3, 10) # (seq_len, batch, input_size) >>> h0 = torch.zeros(2, 3, 20) >>> out, hn = rnn(x, h0)
- __init__(input_size, hidden_size, num_layers=1, dropout=0.0, batch_first=False, **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)Helper method to initialize cells for the derived recurrent layer class.
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
.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
input_size
hidden_size
bias
dropout
batch_first
training