def sample(self, num_samples, context=None, batch_size=None):
"""Generates samples from the distribution. Samples can be generated in batches.
Args:
num_samples: int, number of samples to generate.
context: Tensor or None, conditioning variables. If None, the context is ignored.
batch_size: int or None, number of samples per batch. If None, all samples are generated
in one batch.
Returns:
A Tensor containing the samples, with shape [num_samples, ...] if context is None, or
[context_size, num_samples, ...] if context is given.
"""
if not various.is_positive_int(num_samples):
raise TypeError("Number of samples must be a positive integer.")
if context is not None:
context = torch.as_tensor(context)
if batch_size is None:
return self._sample(num_samples, context)
else:
if not various.is_positive_int(batch_size):
raise TypeError("Batch size must be a positive integer.")
num_batches = num_samples // batch_size
num_leftover = num_samples % batch_size
samples = [
self._sample(batch_size, context) for _ in range(num_batches)
]
if num_leftover > 0:
samples.append(self._sample(num_leftover, context))
return torch.cat(samples, dim=0)
def __init__(self, permutation, dim=1):
if permutation.ndimension() != 1:
raise ValueError("Permutation must be a 1D tensor.")
if not various.is_positive_int(dim):
raise ValueError("dim must be a positive integer.")
super().__init__()
self._dim = dim
self.register_buffer("_permutation", permutation)
def __init__(self, features, num_transforms):
"""Constructor.
Args:
features: int, dimensionality of the input.
num_transforms: int, number of Householder transforms to use.
Raises:
TypeError: if arguments are not the right type.
"""
if not various.is_positive_int(features):
raise TypeError("Number of features must be a positive integer.")
if not various.is_positive_int(num_transforms):
raise TypeError("Number of transforms must be a positive integer.")
super().__init__()
self.features = features
self.num_transforms = num_transforms
# TODO: are randn good initial values?
self.q_vectors = nn.Parameter(torch.randn(num_transforms, features))
def __init__(self, features, using_cache=False):
if not various.is_positive_int(features):
raise TypeError("Number of features must be a positive integer.")
super().__init__()
self.features = features
self.bias = nn.Parameter(torch.zeros(features))
# Caching flag and values.
self.using_cache = using_cache
self.cache = LinearCache()
def __init__(self, features, eps=1e-5, momentum=0.1, affine=True):
if not various.is_positive_int(features):
raise TypeError("Number of features must be a positive integer.")
super().__init__()
self.momentum = momentum
self.eps = eps
constant = np.log(np.exp(1 - eps) - 1)
self.unconstrained_weight = nn.Parameter(constant * torch.ones(features))
self.bias = nn.Parameter(torch.zeros(features))
self.register_buffer("running_mean", torch.zeros(features))
self.register_buffer("running_var", torch.zeros(features))
def __init__(self, num_transforms, split_dim=1):
"""Constructor.
Args:
num_transforms: int, total number of transforms to be added.
split_dim: dimension along which to split.
"""
if not various.is_positive_int(split_dim):
raise TypeError("Split dimension must be a positive integer.")
super().__init__()
self._transforms = nn.ModuleList()
self._output_shapes = []
self._num_transforms = num_transforms
self._split_dim = split_dim
def __init__(self, features):
"""
Transform that performs activation normalization. Works for 2D and 4D inputs. For 4D
inputs (images) normalization is performed per-channel, assuming BxCxHxW input shape.
Reference:
> D. Kingma et. al., Glow: Generative flow with invertible 1x1 convolutions, NeurIPS 2018.
"""
if not various.is_positive_int(features):
raise TypeError("Number of features must be a positive integer.")
super().__init__()
self.initialized = False
self.log_scale = nn.Parameter(torch.zeros(features))
self.shift = nn.Parameter(torch.zeros(features))
def __init__(self, features):
"""
Transform that performs activation normalization. Works for 2D and 4D inputs. For 4D
inputs (images) normalization is performed per-channel, assuming BxCxHxW input shape.
Reference:
> D. Kingma et. al., Glow: Generative flow with invertible 1x1 convolutions, NeurIPS 2018.
"""
if not various.is_positive_int(features):
raise TypeError("Number of features must be a positive integer.")
super().__init__()
self.initialized = False # TODO: this should be a buffer, but I don't want to ruin the already saved models by changing it now
# self.register_buffer("initialized", torch.ones(1, dtype=torch.bool))
self.log_scale = nn.Parameter(torch.zeros(features))
self.shift = nn.Parameter(torch.zeros(features))
def __init__(self, features, dim=1):
if not various.is_positive_int(features):
raise ValueError("Number of features must be a positive integer.")
super().__init__(torch.randperm(features), dim)
