[英]How to get a uniform distribution in a range [r1,r2] in PyTorch?
我想在 PyTorch 中获得一个大小为[a,b]
的二维torch.Tensor
,其中填充了来自均匀分布(在[r1,r2]
范围内)的值。
If U
is a random variable uniformly distributed on [0, 1], then (r1 - r2) * U + r2
is uniformly distributed on [r1, r2].如果
U
是均匀分布在 [0, 1] 上的随机变量,则(r1 - r2) * U + r2
均匀分布在 [r1, r2] 上。
Thus, you just need:因此,您只需要:
(r1 - r2) * torch.rand(a, b) + r2
Alternatively, you can simply use:或者,您可以简单地使用:
torch.FloatTensor(a, b).uniform_(r1, r2)
To fully explain this formulation, let's look at some concrete numbers:为了充分解释这个公式,让我们看一些具体的数字:
r1 = 2 # Create uniform random numbers in half-open interval [2.0, 5.0)
r2 = 5
a = 1 # Create tensor shape 1 x 7
b = 7
We can break down the expression (r1 - r2) * torch.rand(a, b) + r2
as follows:我们可以将表达式
(r1 - r2) * torch.rand(a, b) + r2
如下:
torch.rand(a, b)
produces an axb
(1x7) tensor with numbers uniformly distributed in the range [0.0, 1.0). torch.rand(a, b)
产生一个axb
(1x7) 张量,其数字均匀分布在 [0.0, 1.0) 范围内。x = torch.rand(a, b)
print(x)
# tensor([[0.5671, 0.9814, 0.8324, 0.0241, 0.2072, 0.6192, 0.4704]])
(r1 - r2) * torch.rand(a, b)
produces numbers distributed in the uniform range [0.0, -3.0) (r1 - r2) * torch.rand(a, b)
产生分布在均匀范围 [0.0, -3.0) 内的数字print((r1 - r2) * x)
tensor([[-1.7014, -2.9441, -2.4972, -0.0722, -0.6216, -1.8577, -1.4112]])
(r1 - r2) * torch.rand(a, b) + r2
produces numbers in the uniform range [5.0, 2.0) (r1 - r2) * torch.rand(a, b) + r2
产生统一范围内的数字 [5.0, 2.0)print((r1 - r2) * x + r2)
tensor([[3.2986, 2.0559, 2.5028, 4.9278, 4.3784, 3.1423, 3.5888]])
Now, let's break down the answer suggested by @Jonasson: (r2 - r1) * torch.rand(a, b) + r1
现在,让我们分解@Jonasson 建议的答案:
(r2 - r1) * torch.rand(a, b) + r1
torch.rand(a, b)
produces (1x7) numbers uniformly distributed in the range [0.0, 1.0).torch.rand(a, b)
产生 (1x7) 数字,均匀分布在 [0.0, 1.0) 范围内。x = torch.rand(a, b)
print(x)
# tensor([[0.5671, 0.9814, 0.8324, 0.0241, 0.2072, 0.6192, 0.4704]])
(r2 - r1) * torch.rand(a, b)
produces numbers uniformly distributed in the range [0.0, 3.0). (r2 - r1) * torch.rand(a, b)
产生在 [0.0, 3.0) 范围内均匀分布的数字。print((r2 - r1) * x)
# tensor([[1.7014, 2.9441, 2.4972, 0.0722, 0.6216, 1.8577, 1.4112]])
(r2 - r1) * torch.rand(a, b) + r1
produces numbers uniformly distributed in the range [2.0, 5.0) (r2 - r1) * torch.rand(a, b) + r1
产生在 [2.0, 5.0) 范围内均匀分布的数字print((r2 - r1) * x + r1)
tensor([[3.7014, 4.9441, 4.4972, 2.0722, 2.6216, 3.8577, 3.4112]])
In summary , (r1 - r2) * torch.rand(a, b) + r2
produces numbers in the range [r2, r1), while (r2 - r1) * torch.rand(a, b) + r1
produces numbers in the range [r1, r2).总之,
(r1 - r2) * torch.rand(a, b) + r2
产生范围 [r2, r1) 中的数字,而(r2 - r1) * torch.rand(a, b) + r1
产生范围内的数字范围 [r1, r2)。
torch.FloatTensor(a, b).uniform_(r1, r2)
Utilize the torch.distributions
package to generate samples from different distributions.利用
torch.distributions
包从不同的分布中生成样本。
For example to sample a 2d PyTorch tensor of size [a,b]
from a uniform distribution of range(low, high)
try the following sample code例如,要从
range(low, high)
的均匀分布中采样大小为[a,b]
的 2d PyTorch 张量,请尝试以下示例代码
import torch
a,b = 2,3 #dimension of the pytorch tensor to be generated
low,high = 0,1 #range of uniform distribution
x = torch.distributions.uniform.Uniform(low,high).sample([a,b])
To get a uniform random distribution, you can use要获得均匀的随机分布,您可以使用
torch.distributions.uniform.Uniform()
example,例子,
import torch
from torch.distributions import uniform
distribution = uniform.Uniform(torch.Tensor([0.0]),torch.Tensor([5.0]))
distribution.sample(torch.Size([2,3])
This will give the output, tensor of size [2, 3].这将给出输出,大小为 [2, 3] 的张量。
Please Can you try something like:请你可以尝试类似的东西:
import torch as pt
pt.empty(2,3).uniform_(5,10).type(pt.FloatTensor)
This answer uses NumPy to first produce a random matrix and then converts the matrix to a PyTorch tensor.这个答案使用 NumPy 首先生成一个随机矩阵,然后将矩阵转换为 PyTorch 张量。 I find the NumPy API to be easier to understand.
我发现 NumPy API 更容易理解。
import numpy as np
torch.from_numpy(np.random.uniform(low=r1, high=r2, size=(a, b)))
PyTorch has a number of distributions built in. You can build a tensor of the desired shape
with elements drawn from a uniform distribution like so: PyTorch 内置了许多分布。您可以使用从均匀分布中提取的元素构建所需
shape
的张量,如下所示:
from torch.distributions.uniform import Uniform
shape = 3,4
r1, r2 = 0,1
x = Uniform(r1, r2).sample(shape)
For those who are frustratingly bashing their keyboard yelling "why isn't this working." 对于那些沮丧地抨击他们的键盘的人大喊“为什么这不起作用”。 as I was... note the underscore behind the word uniform.
就像我一样......注意制服这个词背后的下划线。
torch.FloatTensor(a, b).uniform_(r1, r2)
^ here
See this for all distributions: https://pytorch.org/docs/stable/distributions.html#torch.distributions.uniform.Uniform查看所有发行版: https ://pytorch.org/docs/stable/distributions.html#torch.distributions.uniform.Uniform
This is the way I found works:这是我发现工作的方式:
# generating uniform variables
import numpy as np
num_samples = 3
Din = 1
lb, ub = -1, 1
xn = np.random.uniform(low=lb, high=ub, size=(num_samples,Din))
print(xn)
import torch
sampler = torch.distributions.Uniform(low=lb, high=ub)
r = sampler.sample((num_samples,Din))
print(r)
r2 = torch.torch.distributions.Uniform(low=lb, high=ub).sample((num_samples,Din))
print(r2)
# process input
f = nn.Sequential(OrderedDict([
('f1', nn.Linear(Din,Dout)),
('out', nn.SELU())
]))
Y = f(r2)
print(Y)
but I have to admit I don't know what the point of generating sampler is and why not just call it directly as I do in the one liner (last line of code).但我不得不承认我不知道生成采样器的意义何在,为什么不直接调用它,就像我在一个衬里(最后一行代码)中所做的那样。
Comments:注释:
Reference:参考:
Pytorch (now?) has a random integer function that allows: Pytorch(现在?)有一个随机整数函数,它允许:
torch.randint(low=r1, high=r2, size=(1,), **kwargs)
and returns uniformly sampled random integers of shape size in range [r1, r2).并返回 [r1, r2) 范围内形状大小的均匀采样的随机整数。
https://pytorch.org/docs/stable/generated/torch.randint.htmlhttps://pytorch.org/docs/stable/generated/torch.randint.html
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.