161ae41bebc73c146627169f761e3c4ddf83e5d4,pixyz/losses/losses.py,Divergence,__init__,#Divergence#Any#Any#Any#,237

Before Change

        
        if input_var is not None:
            _input_var = deepcopy(input_var)
        else:
            _input_var = deepcopy(p.input_var)
            if q is not None:
                _input_var += deepcopy(q.input_var)

After Change

    >>> p = Generator()
    >>> q = Inference()
    >>> prior = Normal(loc=torch.tensor(0.), scale=torch.tensor(1.),
    ...                var=["z"], features_shape=[64], name="p_{prior}")
    ...
    >>> // Define a loss function (VAE)
    >>> reconst = -p.log_prob().expectation(q)
    >>> kl = KullbackLeibler(q,prior)
    >>> loss_cls = (reconst - kl).mean()

Instances