CODEWITHSUNDEEP
pythonpytorchuniform-distribution
Bishwajit Purkaystha
Bishwajit Purkaystha

Reputation: 2195

How to get a uniform distribution in a range [r1,r2] in PyTorch?

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.

Upvotes: 64

Views: 120007

Answers (9)

LSgeo
LSgeo

Reputation: 511

Pytorch (now?) has a random integer function that allows:

torch.randint(low=r1, high=r2, size=(1,), **kwargs)

and returns uniformly sampled random integers of shape size in range [r1, r2).

https://pytorch.org/docs/stable/generated/torch.randint.html

Upvotes: 1

Sunil
Sunil

Reputation: 181

Please Can you try something like:

import torch as pt
pt.empty(2,3).uniform_(5,10).type(pt.FloatTensor)

Upvotes: 4

Charlie Parker
Charlie Parker

Reputation: 5169

See this for all distributions: https://pytorch.org/docs/stable/distributions.html#torch.distributions.uniform.Uniform

This is the way I found works:

# 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).

Comments:

Reference:

Upvotes: 0

stackoverflowuser2010
stackoverflowuser2010

Reputation: 40969

This answer uses NumPy to first produce a random matrix and then converts the matrix to a PyTorch tensor. I find the NumPy API to be easier to understand.

import numpy as np

torch.from_numpy(np.random.uniform(low=r1, high=r2, size=(a, b)))

Upvotes: 2

Gaurav Shrivastava
Gaurav Shrivastava

Reputation: 943

Utilize the torch.distributions package to generate samples from different distributions.

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

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])

Upvotes: 11

iacob
iacob

Reputation: 24261

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:

from torch.distributions.uniform import Uniform

shape = 3,4
r1, r2 = 0,1

x = Uniform(r1, r2).sample(shape)

Upvotes: 4

BiBi
BiBi

Reputation: 7908

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

Thus, you just need:

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

Alternatively, you can simply use:

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

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

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

  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) 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 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]])

Now, let's break down the answer suggested by @Jonasson: (r2 - r1) * torch.rand(a, b) + r1

  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) 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 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]])

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).

Upvotes: 97

Pratik_Katte
Pratik_Katte

Reputation: 21

To get a uniform random distribution, you can use

torch.distributions.uniform.Uniform()

example,

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].

Upvotes: 2

rafaelvalle
rafaelvalle

Reputation: 7063

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

Upvotes: 36

Related Questions