net.py 文件源码

def get_loss_func(self, C=1.0, k=1, train=True):
        """Get loss function of VAE.

        The loss value is equal to ELBO (Evidence Lower Bound)
        multiplied by -1.

        Args:
            C (int): Usually this is 1.0. Can be changed to control the
                second term of ELBO bound, which works as regularization.
            k (int): Number of Monte Carlo samples used in encoded vector.
            train (bool): If true loss_function is used for training.
        """
        def lf(x):
            mu, ln_var = self.encode(x)
            batchsize = len(mu.data)
            # reconstruction loss
            rec_loss = 0
            for l in six.moves.range(k):
                z = F.gaussian(mu, ln_var)
                rec_loss += F.bernoulli_nll(x, self.decode(z, sigmoid=False)) \
                    / (k * batchsize)
            self.rec_loss = rec_loss
            self.loss = self.rec_loss + \
                C * gaussian_kl_divergence(mu, ln_var) / batchsize
            return self.loss
        return lf