View source on GitHub
|
Distributions, based on tfp.distributions.Distribution.
Classes
class DeepFactorized: Fully factorized distribution based on neural network cumulative.
class MonotonicAdapter: Adapt a continuous distribution via an ascending monotonic function.
class NoisyDeepFactorized: DeepFactorized that is convolved with uniform noise.
class NoisyLaplace: Laplacian distribution with additive i.i.d. uniform noise.
class NoisyLogistic: Logistic distribution with additive i.i.d. uniform noise.
class NoisyLogisticMixture: Mixture of logistic distributions with additive i.i.d. uniform noise.
class NoisyMixtureSameFamily: Mixture of distributions with additive i.i.d. uniform noise.
class NoisyNormal: Gaussian distribution with additive i.i.d. uniform noise.
class NoisyNormalMixture: Mixture of normal distributions with additive i.i.d. uniform noise.
class NoisyRoundedDeepFactorized: Rounded DeepFactorized + uniform noise.
class NoisyRoundedNormal: Rounded normal distribution + uniform noise.
class NoisySoftRoundedDeepFactorized: Soft rounded DeepFactorized + uniform noise.
class NoisySoftRoundedNormal: Soft rounded normal distribution + uniform noise.
class RoundAdapter: Continuous density function + round.
class SoftRoundAdapter: Differentiable approximation to round.
class UniformNoiseAdapter: Additive i.i.d. uniform noise adapter distribution.
Functions
estimate_tails(...): Estimates approximate tail quantiles.
lower_tail(...): Approximates lower tail quantile for range coding.
quantization_offset(...): Computes distribution-dependent quantization offset.
upper_tail(...): Approximates upper tail quantile for range coding.