FM / distributions

/usr/local/lib64/python3.6/site-packages/torch/distributions/

/usr/local/lib64/python3.6/site-packages/torch/distributions

Name	Size	Mode	Actions
__pycache__/	-	0755	rm
bernoulli.py	3904	0644	edit dl rm
beta.py	3406	0644	edit dl rm
binomial.py	5179	0644	edit dl rm
categorical.py	5488	0644	edit dl rm
cauchy.py	2714	0644	edit dl rm
chi2.py	909	0644	edit dl rm
constraints.py	17288	0644	edit dl rm
constraint_registry.py	10234	0644	edit dl rm
continuous_bernoulli.py	8532	0644	edit dl rm
dirichlet.py	3584	0644	edit dl rm
distribution.py	11735	0644	edit dl rm
exponential.py	2525	0644	edit dl rm
exp_family.py	2275	0644	edit dl rm
fishersnedecor.py	3152	0644	edit dl rm
gamma.py	3121	0644	edit dl rm
geometric.py	4266	0644	edit dl rm
gumbel.py	2528	0644	edit dl rm
half_cauchy.py	2257	0644	edit dl rm
half_normal.py	2058	0644	edit dl rm
independent.py	4361	0644	edit dl rm
kl.py	29998	0644	edit dl rm
kumaraswamy.py	2927	0644	edit dl rm
laplace.py	3054	0644	edit dl rm
lkj_cholesky.py	6124	0644	edit dl rm
logistic_normal.py	1983	0644	edit dl rm
log_normal.py	1772	0644	edit dl rm
lowrank_multivariate_normal.py	9930	0644	edit dl rm
mixture_same_family.py	8636	0644	edit dl rm
multinomial.py	4776	0644	edit dl rm
multivariate_normal.py	10548	0644	edit dl rm
negative_binomial.py	4091	0644	edit dl rm
normal.py	3351	0644	edit dl rm
one_hot_categorical.py	4375	0644	edit dl rm
pareto.py	2057	0644	edit dl rm
poisson.py	2066	0644	edit dl rm
relaxed_bernoulli.py	5360	0644	edit dl rm
relaxed_categorical.py	5202	0644	edit dl rm
studentT.py	3550	0644	edit dl rm
transformed_distribution.py	8270	0644	edit dl rm
transforms.py	38408	0644	edit dl rm
uniform.py	3112	0644	edit dl rm
utils.py	6196	0644	edit dl rm
von_mises.py	5091	0644	edit dl rm
weibull.py	2854	0644	edit dl rm
__init__.py	5884	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/torch/distributions/utils.py (6196B)

from functools import update_wrapper
from numbers import Number
import torch
import torch.nn.functional as F
from typing import Dict, Any
from torch.overrides import has_torch_function

euler_constant = 0.57721566490153286060  # Euler Mascheroni Constant

def broadcast_all(*values):
    r"""
    Given a list of values (possibly containing numbers), returns a list where each
    value is broadcasted based on the following rules:
      - `torch.*Tensor` instances are broadcasted as per :ref:`_broadcasting-semantics`.
      - numbers.Number instances (scalars) are upcast to tensors having
        the same size and type as the first tensor passed to `values`.  If all the
        values are scalars, then they are upcasted to scalar Tensors.

Args:
        values (list of `numbers.Number`, `torch.*Tensor` or objects implementing __torch_function__)

Raises:
        ValueError: if any of the values is not a `numbers.Number` instance,
            a `torch.*Tensor` instance, or an instance implementing __torch_function__
    """
    if not all(isinstance(v, torch.Tensor) or has_torch_function((v,)) or isinstance(v, Number)
               for v in values):
        raise ValueError('Input arguments must all be instances of numbers.Number, '
                         'torch.Tensor or objects implementing __torch_function__.')
    if not all([isinstance(v, torch.Tensor) or has_torch_function((v,)) for v in values]):
        options: Dict[str, Any] = dict(dtype=torch.get_default_dtype())
        for value in values:
            if isinstance(value, torch.Tensor):
                options = dict(dtype=value.dtype, device=value.device)
                break
        new_values = [v if isinstance(v, torch.Tensor) or has_torch_function((v,)) else torch.tensor(v, **options)
                      for v in values]
        return torch.broadcast_tensors(*new_values)
    return torch.broadcast_tensors(*values)

def _standard_normal(shape, dtype, device):
    if torch._C._get_tracing_state():
        # [JIT WORKAROUND] lack of support for .normal_()
        return torch.normal(torch.zeros(shape, dtype=dtype, device=device),
                            torch.ones(shape, dtype=dtype, device=device))
    return torch.empty(shape, dtype=dtype, device=device).normal_()

def _sum_rightmost(value, dim):
    r"""
    Sum out ``dim`` many rightmost dimensions of a given tensor.

Args:
        value (Tensor): A tensor of ``.dim()`` at least ``dim``.
        dim (int): The number of rightmost dims to sum out.
    """
    if dim == 0:
        return value
    required_shape = value.shape[:-dim] + (-1,)
    return value.reshape(required_shape).sum(-1)

def logits_to_probs(logits, is_binary=False):
    r"""
    Converts a tensor of logits into probabilities. Note that for the
    binary case, each value denotes log odds, whereas for the
    multi-dimensional case, the values along the last dimension denote
    the log probabilities (possibly unnormalized) of the events.
    """
    if is_binary:
        return torch.sigmoid(logits)
    return F.softmax(logits, dim=-1)

def clamp_probs(probs):
    eps = torch.finfo(probs.dtype).eps
    return probs.clamp(min=eps, max=1 - eps)

def probs_to_logits(probs, is_binary=False):
    r"""
    Converts a tensor of probabilities into logits. For the binary case,
    this denotes the probability of occurrence of the event indexed by `1`.
    For the multi-dimensional case, the values along the last dimension
    denote the probabilities of occurrence of each of the events.
    """
    ps_clamped = clamp_probs(probs)
    if is_binary:
        return torch.log(ps_clamped) - torch.log1p(-ps_clamped)
    return torch.log(ps_clamped)

class lazy_property:
    r"""
    Used as a decorator for lazy loading of class attributes. This uses a
    non-data descriptor that calls the wrapped method to compute the property on
    first call; thereafter replacing the wrapped method into an instance
    attribute.
    """
    def __init__(self, wrapped):
        self.wrapped = wrapped
        update_wrapper(self, wrapped)

def __get__(self, instance, obj_type=None):
        if instance is None:
            return _lazy_property_and_property(self.wrapped)
        with torch.enable_grad():
            value = self.wrapped(instance)
        setattr(instance, self.wrapped.__name__, value)
        return value

class _lazy_property_and_property(lazy_property, property):
    """We want lazy properties to look like multiple things.

* property when Sphinx autodoc looks
    * lazy_property when Distribution validate_args looks
    """
    def __init__(self, wrapped):
        return property.__init__(self, wrapped)

def tril_matrix_to_vec(mat, diag=0):
    r"""
    Convert a `D x D` matrix or a batch of matrices into a (batched) vector
    which comprises of lower triangular elements from the matrix in row order.
    """
    n = mat.shape[-1]
    if not torch._C._get_tracing_state() and (diag < -n or diag >= n):
        raise ValueError(f'diag ({diag}) provided is outside [{-n}, {n-1}].')
    arange = torch.arange(n, device=mat.device)
    tril_mask = arange < arange.view(-1, 1) + (diag + 1)
    vec = mat[..., tril_mask]
    return vec

def vec_to_tril_matrix(vec, diag=0):
    r"""
    Convert a vector or a batch of vectors into a batched `D x D`
    lower triangular matrix containing elements from the vector in row order.
    """
    # +ve root of D**2 + (1+2*diag)*D - |diag| * (diag+1) - 2*vec.shape[-1] = 0
    n = (-(1 + 2 * diag) + ((1 + 2 * diag)**2 + 8 * vec.shape[-1] + 4 * abs(diag) * (diag + 1))**0.5) / 2
    eps = torch.finfo(vec.dtype).eps
    if not torch._C._get_tracing_state() and (round(n) - n > eps):
        raise ValueError(f'The size of last dimension is {vec.shape[-1]} which cannot be expressed as ' +
                         'the lower triangular part of a square D x D matrix.')
    n = torch.round(n).long() if isinstance(n, torch.Tensor) else round(n)
    mat = vec.new_zeros(vec.shape[:-1] + torch.Size((n, n)))
    arange = torch.arange(n, device=vec.device)
    tril_mask = arange < arange.view(-1, 1) + (diag + 1)
    mat[..., tril_mask] = vec
    return mat

cmd: