model.py 文件源码

def calc_log_posterior(theta, x, n=None):
    """Calculate unnormalized log posterior, ``log p(theta | x) + C``

    Args:
        theta(chainer.Variable): model parameters
        x(numpy.ndarray): sample data
        n(int): total data size
    Returns:
        chainer.Variable: Variable that holding unnormalized log posterior,
        ``log p(theta | x) + C`` of shape ``()``
    """

    theta1, theta2 = F.split_axis(theta, 2, 0)
    log_prior1 = F.sum(F.log(gaussian.gaussian_likelihood(theta1, 0, VAR1)))
    log_prior2 = F.sum(F.log(gaussian.gaussian_likelihood(theta2, 0, VAR2)))
    prob1 = gaussian.gaussian_likelihood(x, theta1, VAR_X)
    prob2 = gaussian.gaussian_likelihood(x, theta1 + theta2, VAR_X)
    log_likelihood = F.sum(F.log(prob1 / 2 + prob2 / 2))
    if n is not None:
        log_likelihood *= n / len(x)
    return log_prior1 + log_prior2 + log_likelihood