Class LSTMCell

imperative/python/megengine/module/rnn.py:124–198

r"""A long short-term memory (LSTM) cell. .. math:: \begin{array}{ll} i = \sigma(W_{ii} x + b_{ii} + W_{hi} h + b_{hi}) \\ f = \sigma(W_{if} x + b_{if} + W_{hf} h + b_{hf}) \\ g = \tanh(W_{ig} x + b_{ig} + W_{hg} h + b_{hg}) \\ o = \sigma(W_{io} x + b_{i

class LSTMCell(RNNCellBase):

    r"""A long short-term memory (LSTM) cell.

    .. math::

        \begin{array}{ll}
        i = \sigma(W_{ii} x + b_{ii} + W_{hi} h + b_{hi}) \\
        f = \sigma(W_{if} x + b_{if} + W_{hf} h + b_{hf}) \\
        g = \tanh(W_{ig} x + b_{ig} + W_{hg} h + b_{hg}) \\
        o = \sigma(W_{io} x + b_{io} + W_{ho} h + b_{ho}) \\
        c' = f * c + i * g \\
        h' = o * \tanh(c') \\
        \end{array}

    where :math:`\sigma` is the sigmoid function, and :math:`*` is the Hadamard product.

    Args:
        input_size(:class:`int`): The number of expected features in the input `x`
        hidden_size(:class:`int`): The number of features in the hidden state `h`
        bias(:class:`bool`): If ``False``, then the layer does not use bias weights `b_ih` and
            `b_hh`. Default: ``True``

    Shape:
        - Inputs: input, (h_0, c_0)
            input: `(batch, input_size)`. Tensor containing input features.
            h_0: `(batch, hidden_size)`. Tensor containing the initial hidden state for each element in the batch.
            c_0: `(batch, hidden_size)`. Tensor containing the initial cell state for each element in the batch.
            If `(h_0, c_0)` is not provided, both **h_0** and **c_0** default to zero.

        - Outputs: (h_1, c_1)
            h_1: `(batch, hidden_size)`. Tensor containing the next hidden state for each element in the batch.
            c_1: `(batch, hidden_size)`. Tensor containing the next cell state for each element in the batch.

    Examples:

        .. code-block::

            import numpy as np
            import megengine as mge
            import megengine.module as M

            m = M.LSTMCell(10, 20)
            inp = mge.tensor(np.random.randn(3, 10), dtype=np.float32)
            hx = mge.tensor(np.random.randn(3, 20), dtype=np.float32)
            cx = mge.tensor(np.random.randn(3, 20), dtype=np.float32)
            hy, cy = m(inp, (hx, cx))
            print(hy.numpy().shape)
            print(cy.numpy().shape)

        Outputs:

        .. code-block::

            (3, 20)
            (3, 20)

    """