如何在 PyTorch 中获得 [r1,r2] 范围内的均匀分布?

How to get a uniform distribution in a range [r1,r2] in PyTorch?(如何在 PyTorch 中获得 [r1,r2] 范围内的均匀分布?)

问题描述

我想得到一个大小为 [a,b] 的二维 torch.Tensor 填充了来自均匀分布的值(范围 [r1,r2]) 在 PyTorch 中.

I want to get a 2-D torch.Tensor with size [a,b] filled with values from a uniform distribution (in range [r1,r2]) in PyTorch.

推荐答案

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.

If U is a random variable uniformly distributed on [0, 1], then (r1 - r2) * U + r2 is uniformly distributed on [r1, r2].

因此，您只需要:

(r1 - r2) * torch.rand(a, b) + r2

或者，您可以简单地使用:

Alternatively, you can simply use:

torch.FloatTensor(a, b).uniform_(r1, r2)

<小时>

为了充分解释这个公式，让我们看一些具体的数字:

---

To fully explain this formulation, let's look at some concrete numbers:

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

我们可以将表达式 (r1 - r2) * torch.rand(a, b) + r2 分解如下:

We can break down the expression (r1 - r2) * torch.rand(a, b) + r2 as follows:

1. torch.rand(a, b) 产生一个 a x b (1x7) 张量，其数字均匀分布在 [0.0, 1.0 范围内.

1. torch.rand(a, b) produces an a x b (1x7) tensor with numbers uniformly distributed in the range [0.0, 1.0).

x = torch.rand(a, b)
print(x)
# tensor([[0.5671, 0.9814, 0.8324, 0.0241, 0.2072, 0.6192, 0.4704]])

1. (r1 - r2) * torch.rand(a, b) 生成分布在统一范围 [0.0, -3.0) 中的数字

1. (r1 - r2) * torch.rand(a, b) produces numbers distributed in the uniform range [0.0, -3.0)

print((r1 - r2) * x)
tensor([[-1.7014, -2.9441, -2.4972, -0.0722, -0.6216, -1.8577, -1.4112]])

1. (r1 - r2) * torch.rand(a, b) + r2 生成统一范围内的数字 [5.0, 2.0)

1. (r1 - r2) * torch.rand(a, b) + r2 produces numbers in the uniform range [5.0, 2.0)

print((r1 - r2) * x + r2)
tensor([[3.2986, 2.0559, 2.5028, 4.9278, 4.3784, 3.1423, 3.5888]])

<小时>

现在，让我们分解@Jonasson 建议的答案:(r2 - r1) * torch.rand(a, b) + r1

1. 同样，torch.rand(a, b) 生成 (1x7) 均匀分布在 [0.0, 1.0] 范围内的数字.

1. Again, torch.rand(a, b) produces (1x7) numbers uniformly distributed in the range [0.0, 1.0).

x = torch.rand(a, b)
print(x)
# tensor([[0.5671, 0.9814, 0.8324, 0.0241, 0.2072, 0.6192, 0.4704]])

1. (r2 - r1) * torch.rand(a, b) 生成均匀分布在 [0.0, 3.0 范围内的数字.

1. (r2 - r1) * torch.rand(a, b) produces numbers uniformly distributed in the range [0.0, 3.0).

print((r2 - r1) * x)
# tensor([[1.7014, 2.9441, 2.4972, 0.0722, 0.6216, 1.8577, 1.4112]])

1. (r2 - r1) * torch.rand(a, b) + r1 生成在 [2.0, 5.0) 范围内均匀分布的数字

1. (r2 - r1) * torch.rand(a, b) + r1 produces numbers uniformly distributed in the range [2.0, 5.0)

print((r2 - r1) * x + r1)
tensor([[3.7014, 4.9441, 4.4972, 2.0722, 2.6216, 3.8577, 3.4112]])

总结，(r1 - r2) * torch.rand(a, b) + r2 生成范围 [r2, r1) 内的数字，而 (r2 - r1) * torch.rand(a, b) + r1 生成 [r1, r2 范围内的数字.

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).

这篇关于如何在 PyTorch 中获得 [r1,r2] 范围内的均匀分布?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持编程学习网！