Method __init__

python/singa/layer.py:1134–1170

Args: input_size (int): The number of expected features in the input x hidden_size (int): The number of features in the hidden state h num_layers (int): Number of recurrent layers. Default: 1 nonlinearity (string): The non-linearity to use.

(
        self,
        input_size,
        hidden_size,
        num_layers=1,
        nonlinearity="tanh",
        bias=True,
        batch_first=False,
        dropout=0,
        bidirectional=False,
    )

    """

    def __init__(
        self,
        input_size,
        hidden_size,
        num_layers=1,
        nonlinearity="tanh",
        bias=True,
        batch_first=False,
        dropout=0,
        bidirectional=False,
    ):
        """
        Args:
            input_size (int):  The number of expected features in the input x
            hidden_size (int): The number of features in the hidden state h
            num_layers (int):  Number of recurrent layers. Default: 1
            nonlinearity (string): The non-linearity to use. Default: 'tanh'
            bias (bool):  If False, then the layer does not use bias weights.
                Default: True
            batch_first (bool):  If True, then the input and output tensors
                are provided as (batch, seq, feature). Default: False
            dropout (float): If non-zero, introduces a Dropout layer on the
                outputs of each RNN layer except the last layer, with dropout
                probability equal to dropout. Default: 0
            bidirectional (bool): If True, becomes a bidirectional RNN.
                Default: False
        """
        super(RNN, self).__init__()

        self.input_size = input_size
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.nonlinearity = nonlinearity
        self.bias = bias
        self.batch_first = batch_first
        self.dropout = dropout
        self.bidirectional = bidirectional

    def initialize(self, xs, h0):
        Wx_shape = (self.input_size, self.hidden_size)