import torch
torch.rand 0-1均匀分布
"""
Docstring:
rand(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) -> Tensor
Returns a tensor filled with random numbers from a uniform distribution
on the interval :math:`[0, 1)`
The shape of the tensor is defined by the variable argument :attr:`size`.
Args:
size (int...): a sequence of integers defining the shape of the output tensor.
Can be a variable number of arguments or a collection like a list or tuple.
Keyword args:
out (Tensor, optional): the output tensor.
dtype (:class:`torch.dtype`, optional): the desired data type of returned tensor.
Default: if ``None``, uses a global default (see :func:`torch.set_default_tensor_type`).
layout (:class:`torch.layout`, optional): the desired layout of returned Tensor.
Default: ``torch.strided``.
device (:class:`torch.device`, optional): the desired device of returned tensor.
Default: if ``None``, uses the current device for the default tensor type
(see :func:`torch.set_default_tensor_type`). :attr:`device` will be the CPU
for CPU tensor types and the current CUDA device for CUDA tensor types.
requires_grad (bool, optional): If autograd should record operations on the
returned tensor. Default: ``False``.
Example::
>>> torch.rand(4)
tensor([ 0.5204, 0.2503, 0.3525, 0.5673])
>>> torch.rand(2, 3)
tensor([[ 0.8237, 0.5781, 0.6879],
[ 0.3816, 0.7249, 0.0998]])
Type: builtin_function_or_method
"""
# [0, 1)之间的均匀分布
pass
torch.rand([2, 3])
tensor([[0.7589, 0.2792, 0.2308],
[0.1568, 0.1513, 0.7230]])
torch.empty([2, 3]).uniform_(0, 1)
tensor([[0.5647, 0.7497, 0.1139],
[0.1436, 0.9677, 0.3738]])
torch.randn 标准正态分布
"""
Docstring:
randn(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) -> Tensor
Returns a tensor filled with random numbers from a normal distribution
with mean `0` and variance `1` (also called the standard normal
distribution).
.. math::
\text{out}_{i} \sim \mathcal{N}(0, 1)
The shape of the tensor is defined by the variable argument :attr:`size`.
Args:
size (int...): a sequence of integers defining the shape of the output tensor.
Can be a variable number of arguments or a collection like a list or tuple.
Keyword args:
out (Tensor, optional): the output tensor.
dtype (:class:`torch.dtype`, optional): the desired data type of returned tensor.
Default: if ``None``, uses a global default (see :func:`torch.set_default_tensor_type`).
layout (:class:`torch.layout`, optional): the desired layout of returned Tensor.
Default: ``torch.strided``.
device (:class:`torch.device`, optional): the desired device of returned tensor.
Default: if ``None``, uses the current device for the default tensor type
(see :func:`torch.set_default_tensor_type`). :attr:`device` will be the CPU
for CPU tensor types and the current CUDA device for CUDA tensor types.
requires_grad (bool, optional): If autograd should record operations on the
returned tensor. Default: ``False``.
Example::
>>> torch.randn(4)
tensor([-2.1436, 0.9966, 2.3426, -0.6366])
>>> torch.randn(2, 3)
tensor([[ 1.5954, 2.8929, -1.0923],
[ 1.1719, -0.4709, -0.1996]])
Type: builtin_function_or_method
"""
# 标准正态分布
torch.randn([2, 3])
tensor([[ 1.0449, 0.9979, 0.1418],
[-2.3884, -0.8895, 0.9523]])
torch.randint 区间整数随机分布
"""
Docstring:
randint(low=0, high, size, \*, generator=None, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) -> Tensor
Returns a tensor filled with random integers generated uniformly
between :attr:`low` (inclusive) and :attr:`high` (exclusive).
The shape of the tensor is defined by the variable argument :attr:`size`.
.. note:
With the global dtype default (``torch.float32``), this function returns
a tensor with dtype ``torch.int64``.
Args:
low (int, optional): Lowest integer to be drawn from the distribution. Default: 0.
high (int): One above the highest integer to be drawn from the distribution.
size (tuple): a tuple defining the shape of the output tensor.
Keyword args:
generator (:class:`torch.Generator`, optional): a pseudorandom number generator for sampling
out (Tensor, optional): the output tensor.
dtype (:class:`torch.dtype`, optional): the desired data type of returned tensor.
Default: if ``None``, uses a global default (see :func:`torch.set_default_tensor_type`).
layout (:class:`torch.layout`, optional): the desired layout of returned Tensor.
Default: ``torch.strided``.
device (:class:`torch.device`, optional): the desired device of returned tensor.
Default: if ``None``, uses the current device for the default tensor type
(see :func:`torch.set_default_tensor_type`). :attr:`device` will be the CPU
for CPU tensor types and the current CUDA device for CUDA tensor types.
requires_grad (bool, optional): If autograd should record operations on the
returned tensor. Default: ``False``.
Example::
>>> torch.randint(3, 5, (3,))
tensor([4, 3, 4])
>>> torch.randint(10, (2, 2))
tensor([[0, 2],
[5, 5]])
>>> torch.randint(3, 10, (2, 2))
tensor([[4, 5],
[6, 7]])
Type: builtin_function_or_method
"""
# [low, high)随机整数
torch.randint(low=0, high=10, size=[2, 3])
tensor([[3, 8, 8],
[7, 9, 1]])
torch.bernoulli 从伯努利分布中提取二进制随机数（0或1）
Docstring:
bernoulli(input, *, generator=None, out=None) -> Tensor
Draws binary random numbers (0 or 1) from a Bernoulli distribution.
The :attr:input tensor should be a tensor containing probabilities
to be used for drawing the binary random number.
Hence, all values in :attr:input have to be in the range:
:math:0 \leq \text{input}_i \leq 1.
The :math:\text{i}^{th} element of the output tensor will draw a
value :math:1 according to the :math:\text{i}^{th} probability value given
in :attr:input.
.. math::
\text{out}{i} \sim \mathrm{Bernoulli}(p = \text{input})
The returned :attr:out tensor only has values 0 or 1 and is of the same
shape as :attr:input.
:attr:out can have integral dtype, but :attr:input must have floating
point dtype.
Args:
input (Tensor): the input tensor of probability values for the Bernoulli distribution
Keyword args:
generator (:class:torch.Generator, optional): a pseudorandom number generator for sampling
out (Tensor, optional): the output tensor.
Example::
>>> a = torch.empty(3, 3).uniform_(0, 1) # generate a uniform random matrix with range [0, 1]
>>> a
tensor([[ 0.1737, 0.0950, 0.3609],
[ 0.7148, 0.0289, 0.2676],
[ 0.9456, 0.8937, 0.7202]])
>>> torch.bernoulli(a)
tensor([[ 1., 0., 0.],
[ 0., 0., 0.],
[ 1., 1., 1.]])
>>> a = torch.ones(3, 3) # probability of drawing "1" is 1
>>> torch.bernoulli(a)
tensor([[ 1., 1., 1.],
[ 1., 1., 1.],
[ 1., 1., 1.]])
>>> a = torch.zeros(3, 3) # probability of drawing "1" is 0
>>> torch.bernoulli(a)
tensor([[ 0., 0., 0.],
[ 0., 0., 0.],
[ 0., 0., 0.]])
Type: builtin_function_or_method
torch.ones(3,3).uniform_(0, 1)
tensor([[0.4097, 0.6395, 0.4441],
[0.0644, 0.9323, 0.7877],
[0.6428, 0.8769, 0.1398]])
torch.rand([3, 3]).uniform_(0,1)
tensor([[0.4031, 0.0478, 0.7641],
[0.2450, 0.5245, 0.2092],
[0.4752, 0.0585, 0.9410]])
torch.bernoulli(torch.full([1, 20], 0.8))
tensor([[1., 0., 1., 1., 1., 0., 1., 1., 1., 1., 0., 1., 1., 1., 0., 1., 1., 1.,
0., 1.]])
a = torch.tensor([[1.0, 3.3, 6.0],[2,3,6.4]])
a
tensor([[1.0000, 3.3000, 6.0000],
[2.0000, 3.0000, 6.4000]])
aa = a.numpy()
aa[0]
array([1. , 3.3, 6. ], dtype=float32)
aa[1]
array([2. , 3. , 6.4], dtype=float32)
aa[0] < aa[1]
array([ True, False, True])
a[0] < a[1]
tensor([ True, False, True])