core.base_abstractions.distributions#
CategoricalDistr#
class CategoricalDistr(Distr)
A categorical distribution extending PyTorch's Categorical.
FixedNormal#
class FixedNormal(torch.distributions.Normal)
A fixed normal distribution extending PyTorch's Normal.
FixedBernoulli#
class FixedBernoulli(torch.distributions.Bernoulli)
A fixed Bernoulli distribution extending PyTorch's Bernoulli.
DiagGaussian#
class DiagGaussian(nn.Module)
A learned diagonal Gaussian distribution.
Bernoulli#
class Bernoulli(nn.Module)
A learned Bernoulli distribution.
AddBias#
class AddBias(nn.Module)
Adding bias parameters to input values.
AddBias.__init__#
| __init__(bias: torch.FloatTensor)
Initializer.
Parameters
- bias : data to use as the initial values of the bias.
AddBias.forward#
| forward(x: torch.FloatTensor) -> torch.FloatTensor
Adds the stored bias parameters to x.