ops.py 文件源码

def time_distributed_linear(inputs: tf.Tensor,
                            output_size: int,
                            weight_initializer: Optional[Initializer] = None,
                            bias_initializer: Optional[Initializer] = None,
                            name: str = "time_dist_linear") -> tf.Tensor:
    """
    Applies the same linear transformation to all time steps of a sequence.

    Parameters
    ----------
    inputs: tf.Tensor
        The input sequences, of shape [max_time, batch_size, num_features]
    output_size: int
        The desired number of features in the output sequences
    weight_initializer: tf.Initializer, optional
        A custom initializer for the weight matrix of the linear transformation
    bias_initializer: tf.Initializer, optional
        A custom initializer for the bias vector of the linear transformation
    name: str, optional
        A name for the operation (default "time_dist_linear")

    Returns
    -------
    tf.Tensor
        The linearly transformed input sequences, of shape [max_time, batch_size, output_size]
    """
    max_time, batch_size, _ = tf.unstack(tf.shape(inputs))
    static_shape = inputs.shape.as_list()

    with tf.variable_scope(name):
        result = flatten_time(inputs)
        result = linear(result,
                        output_size=output_size,
                        weight_initializer=weight_initializer,
                        bias_initializer=bias_initializer)
        result = restore_time(result, max_time, batch_size, output_size)
        result.set_shape([static_shape[0], static_shape[1], output_size])

        return result