File size: 2,503 Bytes
59630ba | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | from typing import List
import torch
import numpy as np
class DiagonalGaussianDistribution(object):
def __init__(self, parameters, deterministic=False):
self.parameters = parameters
self.mean, self.logvar = torch.chunk(parameters, 2, dim=1)
self.logvar = torch.clamp(self.logvar, -30.0, 20.0)
self.deterministic = deterministic
self.std = torch.exp(0.5 * self.logvar)
self.var = torch.exp(self.logvar)
if self.deterministic:
self.var = self.std = torch.zeros_like(self.mean).to(
device=self.parameters.device
)
def sample(self):
x = self.mean + self.std * torch.randn(self.mean.shape).to(
device=self.parameters.device
)
return x
def kl(self, other=None):
if self.deterministic:
return torch.Tensor([0.0])
else:
dim = [1, 2, 3] if self.mean.dim() == 4 else [1, 3, 4] # BCHW or BCTHW
if other is None:
return 0.5 * torch.sum(
torch.pow(self.mean, 2) + self.var - 1.0 - self.logvar,
dim=dim,
)
else:
return 0.5 * torch.sum(
torch.pow(self.mean - other.mean, 2) / other.var
+ self.var / other.var
- 1.0
- self.logvar
+ other.logvar,
dim=dim,
)
def nll(self, sample, dims=[1, 2, 3]):
if self.deterministic:
return torch.Tensor([0.0])
logtwopi = np.log(2.0 * np.pi)
return 0.5 * torch.sum(
logtwopi + self.logvar + torch.pow(sample - self.mean, 2) / self.var,
dim=dims,
)
def mode(self):
return self.mean
@classmethod
def cat(cls, distributions: List["DiagonalGaussianDistribution"], dim: int = 0):
"""
Concatenates a list of DiagonalGaussianDistributions along the batch dimension.
"""
parameters = torch.cat([dist.parameters for dist in distributions], dim=dim)
all_deterministic = all([dist.deterministic for dist in distributions])
any_deterministic = any([dist.deterministic for dist in distributions])
assert (
all_deterministic == any_deterministic
), "`deterministic` must be the same for all distributions when concatenating."
return cls(parameters, deterministic=all_deterministic)
|