dynamic_lstm¶

paddle.fluid.layers. dynamic_lstm ( input, size, h_0=None, c_0=None, param_attr=None, bias_attr=None, use_peepholes=True, is_reverse=False, gate_activation='sigmoid', cell_activation='tanh', candidate_activation='tanh', dtype='float32', name=None ) [source]

api_attr

Static Graph

Note:

1. This OP only supports LoDTensor as inputs. If you need to deal with Tensor, please use api_fluid_layers_lstm .

2. In order to improve efficiency, users must first map the input of dimension [T, hidden_size] to input of [T, 4 * hidden_size], and then pass it to this OP.

The implementation of this OP include diagonal/peephole connections. Please refer to Gers, F. A., & Schmidhuber, J. (2000) . If you do not need peephole connections, please set use_peepholes to False .

This OP computes each timestep as follows:

$$i_t = \sigma(W_{ix}x_{t} + W_{ih}h_{t-1} + b_{x_i} + b_{h_i})$$

$$f_t = \sigma(W_{fx}x_{t} + W_{fh}h_{t-1} + b_{x_f} + b_{h_f})$$

$$o_t = \sigma(W_{ox}x_{t} + W_{oh}h_{t-1} + b_{x_o} + b_{h_o})$$

$$\widetilde{c_t} = tanh(W_{cx}x_t + W_{ch}h_{t-1} + b{x_c} + b_{h_c})$$

$$c_t = f_t \odot c_{t-1} + i_t \odot \widetilde{c_t}$$

$$h_t = o_t \odot tanh(c_t)$$

The symbolic meanings in the formula are as follows:

• $x_{t}$ represents the input at timestep $t$

• $h_{t}$ represents the hidden state at timestep $t$

• $h_{t-1}, c_{t-1}$ represent the hidden state and cell state at timestep $t-1$ , respectively

• $\widetilde{c_t}$ represents the candidate cell state

• $i_t$ , $f_t$ and $o_t$ represent input gate, forget gate, output gate, respectively

• $W$ represents weight (e.g., $W_{ix}$ is the weight of a linear transformation of input $x_{t}$ when calculating input gate $i_t$ )

• $b$ represents bias (e.g., $b_{i}$ is the bias of input gate)

• $\sigma$ represents nonlinear activation function for gate, default sigmoid

• $\odot$ represents the Hadamard product of a matrix, i.e. multiplying the elements of the same position for two matrices with the same dimension to get another matrix with the same dimension

Parameters

• input (Variable) – LSTM input tensor, multi-dimensional LODTensor of shape $[T, 4*hidden\_size]$ . Data type is float32 or float64.

• size (int) – must be 4 * hidden_size.

• h_0 (Variable , optional) – The initial hidden state of the LSTM, multi-dimensional Tensor of shape $[batch\_size, hidden\_size]$ . Data type is float32 or float64. If set to None, it will be a vector of all 0. Default: None.

• c_0 (Variable , optional) – The initial hidden state of the LSTM, multi-dimensional Tensor of shape $[batch\_size, hidden\_size]$ . Data type is float32 or float64. If set to None, it will be a vector of all 0. h_0 and c_0 can be None but only at the same time. Default: None.

• param_attr (ParamAttr, optional) –

  Parameter attribute of weight. If it is None, the default weight parameter attribute is used. Please refer to ref:api_fluid_ParamAttr’ . If the user needs to set this parameter, the dimension must be :math:`[hidden_size, 4*hidden_size] . Default: None.

  • Weights = $\{ W_{cr},W_{ir},W_{fr},W_{or} \}$ , the shape is [hidden_size, 4*hidden_size].

• bias_attr (ParamAttr, optional) –

  The bias attribute for the learnable bias weights, which contains two parts, input-hidden bias weights and peephole connections weights if setting use_peepholes to True. Please refer to ref:`api_fluid_ParamAttr’ . Default: None.

  System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/fluid/layers/rnn.py:docstring of paddle.fluid.layers.rnn.dynamic_lstm, line 53); backlink

  Inline interpreted text or phrase reference start-string without end-string.

  1. use_peepholes = False - Biases = {$b_c, b_i, b_f, b_o$}. - The shape is [1, 4*hidden_size].

  2. use_peepholes = True - Biases = { :math:`b_c, b_i, b_f, b_o, W_{ic},

     System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/fluid/layers/rnn.py:docstring of paddle.fluid.layers.rnn.dynamic_lstm, line 62); backlink

     Inline interpreted text or phrase reference start-string without end-string.

     System Message: ERROR/3 (/usr/local/lib/python3.8/site-packages/paddle/fluid/layers/rnn.py:docstring of paddle.fluid.layers.rnn.dynamic_lstm, line 64)

     Unexpected indentation.

     W_{fc}, W_{oc}`}.

     System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/fluid/layers/rnn.py:docstring of paddle.fluid.layers.rnn.dynamic_lstm, line 65)

     Block quote ends without a blank line; unexpected unindent.

     • The shape is [1, 7*hidden_size].

• use_peepholes (bool, optional) – Whether to use peephole connection or not. Default: True.

• is_reverse (bool, optional) – Whether to calculate reverse LSTM. Default: False.

• gate_activation (str, optional) – The activation for input gate, forget gate and output gate. Default: “sigmoid”.

• cell_activation (str, optional) – The activation for cell output. Default: “tanh”.

• candidate_activation (str, optional) – The activation for candidate hidden state. Default: “tanh”.

• dtype (str, optional) – Data type, can be “float32” or “float64”. Default: “float32”.

• name (str, optional) – A name for this layer. Please refer to Name . Default: None.

Returns

The hidden state and cell state of LSTM

• hidden: LoDTensor with shape of $[T, hidden\_size]$ , and its lod and dtype is the same as the input.

• cell: LoDTensor with shape of $[T, hidden\_size]$ , and its lod and dtype is the same as the input.

Return type

tuple ( Variable , Variable )

Examples

import paddle.fluid as fluid
emb_dim = 256
vocab_size = 10000
hidden_dim = 512

data = fluid.data(name='x', shape=[None], dtype='int64', lod_level=1)
emb = fluid.embedding(input=data, size=[vocab_size, emb_dim], is_sparse=True)

forward_proj = fluid.layers.fc(input=emb, size=hidden_dim * 4,
                               bias_attr=False)

forward, cell = fluid.layers.dynamic_lstm(
    input=forward_proj, size=hidden_dim * 4, use_peepholes=False)
forward.shape  # (-1, 512)
cell.shape  # (-1, 512)