PyTorch is an open-source framework available with a Python programming language.

A tensor is a multidimensional array that is used to store the data. So for using a Tensor, we have to import the torch module.

To create a tensor, the method used is tensor()”

**Syntax**:

Where data is a multi-dimensional array.

**torch.any()**

torch.any() in PyTorch returns True if at least one element in a tensor is not equal to 0 or False. If all the values in a tensor are equal to 0 or False, it will return False.

It takes one parameter.

**Syntax**:

**Parameter**:

tensor_object is a tensor.

**Example 1**

In this example, we will create a tensor with one dimension with 5 elements and apply any() function to check the functionality.

import torch

#create a 1D tensor

data1 = torch.tensor([2,3,0,3,4])

#display

print("Actual elements in the Tensor: ")

print(data1)

print("Any of the elements in a tensor not equal to 0? ")

#any() in pytorch

print(torch.any(data1))

Output:

tensor([2, 3, 0, 3, 4])

Are any of the elements in a tensor not equal to 0?

tensor(True)

Here, we can find 2,3,3 and 4 non-zero elements present in the tensor. So any() returned True.

**Example 2**

In this example, we will create a tensor with one dimension that has 5 elements and apply any() function to check the functionality.

import torch

#create a 1D tensor

data1 = torch.tensor([0,0,0,0,0])

#display

print("Actual elements in the Tensor: ")

print(data1)

print("Any of the elements in a tensor not equal to 0? ")

#any() in pytorch

print(torch.any(data1))

Output:

tensor([0, 0, 0, 0, 0])

Are any of the elements in a tensor not equal to 0?

tensor(False)

Here, we can find all zero elements in the tensor. So any() returned False.

**Example 3**

In this example, we will create a tensor with one dimension that has 5 boolean elements and apply any() function to check the functionality.

import torch

#create a 1D tensor

data1 = torch.tensor([True,False,False,False,False])

#display

print("Actual elements in the Tensor: ")

print(data1)

print("Any of the elements in a tensor not equal to False? ")

#any() in pytorch

print(torch.any(data1))

Output:

tensor([ True, False, False, False, False])

Are any of the elements in a tensor not equal to False?

tensor(True)

Here, we can find at least one True in the tensor. So the any() returned True.

**Work With CPU**

If you want to run any() function on the CPU, then we have to create a tensor with a cpu() function. This will run on a CPU machine.

When we are creating a tensor, at this time, we can use the cpu() function.

**Syntax**:

**Example 1**

In this example, we will create a tensor with one dimension that has 5 elements on the cpu and apply any() function to check the functionality.

import torch

#create a 1D tensor

data1 = torch.tensor([2,3,0,3,4]).cpu()

#display

print("Actual elements in the Tensor: ")

print(data1)

print("Any of the elements in a tensor not equal to 0? ")

#any() in pytorch

print(torch.any(data1))

Output:

tensor([2, 3, 0, 3, 4])

Are any of the elements in a tensor not equal to 0?

tensor(True)

Here, we can find 2,3,3 and 4 non-zero elements present in the tensor. So any() returned True.

**Example 2**

In this example, we will create a tensor with one dimension that has 5 elements on the cpu and apply any() function to check the functionality.

import torch

#create a 1D tensor

data1 = torch.tensor([0,0,0,0,0]).cpu()

#display

print("Actual elements in the Tensor: ")

print(data1)

print("Any of the elements in a tensor not equal to 0? ")

#any() in pytorch

print(torch.any(data1))

Output:

tensor([0, 0, 0, 0, 0])

Are any of the elements in a tensor not equal to 0?

tensor(False)

Here, we can find all zero elements in the tensor. So any() returned False.

**Example 3**

In this example, we will create a tensor with one dimension that has 5 boolean elements on the cpu and apply any() function to check the functionality.

import torch

#create a 1D tensor

data1 = torch.tensor([True,False,False,False,False]).cpu()

#display

print("Actual elements in the Tensor: ")

print(data1)

print("Any of the elements in a tensor not equal to False? ")

#any() in pytorch

print(torch.any(data1))

Output:

tensor([ True, False, False, False, False])

Are any of the elements in a tensor not equal to False?

tensor(True)

Here, we can find at least one True in the tensor. So the any() returned True.

**Conclusion**

In this PyTorch lesson, we discussed any() function. It returns True if at least one element in a tensor is not equal to 0 or False. If all the values in a tensor are equal to 0 or False, it will return False. We saw 3 different examples and also worked on these examples on a cpu machine.