Table Of Contents
Table Of Contents


class mxnet.gluon.rnn.GRU(hidden_size, num_layers=1, layout='TNC', dropout=0, bidirectional=False, input_size=0, i2h_weight_initializer=None, h2h_weight_initializer=None, i2h_bias_initializer='zeros', h2h_bias_initializer='zeros', **kwargs)[source]

Applies a multi-layer gated recurrent unit (GRU) RNN to an input sequence. Note: this is an implementation of the cuDNN version of GRUs (slight modification compared to Cho et al. 2014; the reset gate \(r_t\) is applied after matrix multiplication).

For each element in the input sequence, each layer computes the following function:

\[\begin{split}\begin{array}{ll} r_t = sigmoid(W_{ir} x_t + b_{ir} + W_{hr} h_{(t-1)} + b_{hr}) \\ i_t = sigmoid(W_{ii} x_t + b_{ii} + W_{hi} h_{(t-1)} + b_{hi}) \\ n_t = \tanh(W_{in} x_t + b_{in} + r_t * (W_{hn} h_{(t-1)} + b_{hn})) \\ h_t = (1 - i_t) * n_t + i_t * h_{(t-1)} \\ \end{array}\end{split}\]

where \(h_t\) is the hidden state at time t, \(x_t\) is the hidden state of the previous layer at time t or \(input_t\) for the first layer, and \(r_t\), \(i_t\), \(n_t\) are the reset, input, and new gates, respectively.

  • hidden_size (int) – The number of features in the hidden state h

  • num_layers (int, default 1) – Number of recurrent layers.

  • layout (str, default 'TNC') – The format of input and output tensors. T, N and C stand for sequence length, batch size, and feature dimensions respectively.

  • dropout (float, default 0) – If non-zero, introduces a dropout layer on the outputs of each RNN layer except the last layer

  • bidirectional (bool, default False) – If True, becomes a bidirectional RNN.

  • i2h_weight_initializer (str or Initializer) – Initializer for the input weights matrix, used for the linear transformation of the inputs.

  • h2h_weight_initializer (str or Initializer) – Initializer for the recurrent weights matrix, used for the linear transformation of the recurrent state.

  • i2h_bias_initializer (str or Initializer) – Initializer for the bias vector.

  • h2h_bias_initializer (str or Initializer) – Initializer for the bias vector.

  • input_size (int, default 0) – The number of expected features in the input x. If not specified, it will be inferred from input.

  • prefix (str or None) – Prefix of this Block.

  • params (ParameterDict or None) – Shared Parameters for this Block.

  • data: input tensor with shape (sequence_length, batch_size, input_size) when layout is “TNC”. For other layouts, dimensions are permuted accordingly using transpose() operator which adds performance overhead. Consider creating batches in TNC layout during data batching step.

  • states: initial recurrent state tensor with shape (num_layers, batch_size, num_hidden). If bidirectional is True, shape will instead be (2*num_layers, batch_size, num_hidden). If states is None, zeros will be used as default begin states.

  • out: output tensor with shape (sequence_length, batch_size, num_hidden) when layout is “TNC”. If bidirectional is True, output shape will instead be (sequence_length, batch_size, 2*num_hidden)

  • out_states: output recurrent state tensor with the same shape as states. If states is None out_states will not be returned.


>>> layer = mx.gluon.rnn.GRU(100, 3)
>>> layer.initialize()
>>> input = mx.nd.random.uniform(shape=(5, 3, 10))
>>> # by default zeros are used as begin state
>>> output = layer(input)
>>> # manually specify begin state.
>>> h0 = mx.nd.random.uniform(shape=(3, 3, 100))
>>> output, hn = layer(input, h0)
__init__(hidden_size, num_layers=1, layout='TNC', dropout=0, bidirectional=False, input_size=0, i2h_weight_initializer=None, h2h_weight_initializer=None, i2h_bias_initializer='zeros', h2h_bias_initializer='zeros', **kwargs)[source]

Initialize self. See help(type(self)) for accurate signature.


__init__(hidden_size[, num_layers, layout, …])

Initialize self.


Applies fn recursively to every child block as well as self.

begin_state([batch_size, func])

Initial state for this cell.


Cast this Block to use another data type.


Returns a ParameterDict containing this Block and all of its children’s Parameters(default), also can returns the select ParameterDict which match some given regular expressions.

export(path[, epoch])

Export HybridBlock to json format that can be loaded by SymbolBlock.imports, mxnet.mod.Module or the C++ interface.

forward(x, *args)

Defines the forward computation.

hybrid_forward(F, inputs[, states])

Overrides to construct symbolic graph for this Block.


Activates or deactivates HybridBlock s recursively.


Infers shape of Parameters from inputs.


Infers data type of Parameters from inputs.

initialize([init, ctx, verbose, force_reinit])

Initializes Parameter s of this Block and its children.

load_parameters(filename[, ctx, …])

Load parameters from file previously saved by save_parameters.

load_params(filename[, ctx, allow_missing, …])

[Deprecated] Please use load_parameters.


Returns a name space object managing a child Block and parameter names.

register_child(block[, name])

Registers block as a child of self.


Registers a forward hook on the block.


Registers a forward pre-hook on the block.


Save parameters to file.


[Deprecated] Please use save_parameters.



Print the summary of the model’s output and parameters.



Name of this Block, without ‘_’ in the end.


Returns this Block’s parameter dictionary (does not include its children’s parameters).


Prefix of this Block.