def repeat_rows(x, num_reps):
"""Each row of tensor `x` is repeated `num_reps` times along leading dimension."""
if not utils.is_positive_int(num_reps):
raise TypeError('Number of repetitions must be a positive integer.')
shape = x.shape
x = x.unsqueeze(1)
x = x.expand(shape[0], num_reps, *shape[1:])
return merge_leading_dims(x, num_dims=2)
def merge_leading_dims(x, num_dims):
"""Reshapes the tensor `x` such that the first `num_dims` dimensions are merged to one."""
if not utils.is_positive_int(num_dims):
raise TypeError('Number of leading dims must be a positive integer.')
if num_dims > x.dim():
raise ValueError('Number of leading dims can\'t be greater than total number of dims.')
new_shape = torch.Size([-1]) + x.shape[num_dims:]
return torch.reshape(x, new_shape)
def __init__(self, permutation, dim=1):
if permutation.ndimension() != 1:
raise ValueError('Permutation must be a 1D tensor.')
if not utils.is_positive_int(dim):
raise ValueError('dim must be a positive integer.')
super().__init__()
self._dim = dim
self.register_buffer('_permutation', permutation)
def tile(x, n):
if not utils.is_positive_int(n):
raise TypeError('Argument \'n\' must be a positive integer.')
x_ = x.reshape(-1)
x_ = x_.repeat(n)
x_ = x_.reshape(n, -1)
x_ = x_.transpose(1, 0)
x_ = x_.reshape(-1)
return x_
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 utils.is_positive_int(features):
raise TypeError('Number of features must be a positive integer.')
if not utils.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 utils.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 utils.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 utils.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 utils.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, dim=1):
if not utils.is_positive_int(features):
raise ValueError('Number of features must be a positive integer.')
super().__init__(torch.arange(features - 1, -1, -1), dim)
