equal(), eq() and ne() in PyTorch

#pytorch #equal #eq #ne

My post explains gt(), lt(), ge() and le().

equal() can check the 1st 0D or more D tensor is equal to the 2nd 0D or more D tensor as shown below:

*Memos:

equal() can be used with torch or a tensor.
The 1st argument(tensor of int, float, complex or bool) with torch or using a tensor(tensor of int, float, complex or bool) is input(Required).
The 2nd argument(tensor of int, float, complex or bool) with torch or the 1st argument with a tensor(tensor of int, float, complex or bool) is other(Required).

import torch

tensor1 = torch.tensor([5, 9, 3])
tensor2 = torch.tensor([5, 9, 3])

torch.equal(input=tensor1, other=tensor2)
tensor1.equal(other=tensor2)
torch.equal(input=tensor2, other=tensor1)
tensor2.equal(other=tensor1)
# True

tensor1 = torch.tensor([5., 9., 3.])
tensor2 = torch.tensor([5+0j, 9+0j, 3+0j])

torch.equal(input=tensor1, other=tensor2)
torch.equal(input=tensor2, other=tensor1)
# True

tensor1 = torch.tensor([1+0j, 0+0j, 1+0j])
tensor2 = torch.tensor([True, False, True])

torch.equal(input=tensor1, other=tensor2)
torch.equal(input=tensor2, other=tensor1)
# True

tensor1 = torch.tensor([5, 9, 3])
tensor2 = torch.tensor([7, 9, 3])

torch.equal(input=tensor1, other=tensor2)
torch.equal(input=tensor2, other=tensor1)
# False

tensor1 = torch.tensor([5, 9, 3])
tensor2 = torch.tensor([[5, 9, 3]])

torch.equal(input=tensor1, other=tensor2)
torch.equal(input=tensor2, other=tensor1)
# False

eq() can check the zero or more elements of the 1st 0D or more D tensor are equal to the zero or more elements of the 2nd 0D or more D tensor element-wise as shown below:

*Memos:

eq() can be used with torch or a tensor.
The 1st argument(tensor of int, float, complex or bool) with torch or using a tensor(tensor of int, float, complex or bool) is input(Required).
The 2nd argument(tensor of int, float, complex or bool or int, float, complex or bool) with torch or the 1st argument with a tensor(tensor of int, float, complex or bool or int, float, complex or bool) is other(Required).
The result is the higher D tensor which has more elements.

import torch

tensor1 = torch.tensor(5)
tensor2 = torch.tensor([[3, 5, 4],
                        [6, 3, 5]])
torch.eq(input=tensor1, other=tensor2)
tensor1.eq(other=tensor2)
torch.eq(input=tensor2, other=tensor1)
tensor2.eq(other=tensor1)
# tensor([[False, True, False],
#         [False, False, True]])

torch.eq(input=tensor1, other=3)
# tensor(False)

torch.eq(input=tensor2, other=3)
# tensor([[True, False, False],
#         [False, True, False]])

tensor1 = torch.tensor([5, 0, 3])
tensor2 = torch.tensor([[5, 5, 5],
                        [0, 0, 0],
                        [3, 3, 3]])
torch.eq(input=tensor1, other=tensor2)
torch.eq(input=tensor2, other=tensor1)
# tensor([[True, False, False],
#         [False, True, False], 
#         [False, False, True]])

torch.eq(input=tensor1, other=3)
torch.eq(input=tensor1, other=3.)
torch.eq(input=tensor1, other=3+0j)
# tensor([False, False, True])

torch.eq(input=tensor1, other=False)
# tensor([False, True, False])

torch.eq(input=tensor2, other=3)
torch.eq(input=tensor2, other=3.)
torch.eq(input=tensor2, other=3+0j)
# tensor([[False, False, False],
#         [False, False, False],
#         [True, True, True]])

torch.eq(input=tensor2, other=False)
# tensor([[False, False, False],
#         [True, True, True],
#         [False, False, False]])

tensor1 = torch.tensor([5., 0., 3.])
tensor2 = torch.tensor([[5+0j, 5+0j, 5+0j],
                        [0+0j, 0+0j, 0+0j],
                        [3+0j, 3+0j, 3+0j]])
torch.eq(input=tensor1, other=tensor2)
torch.eq(input=tensor2, other=tensor1)
# tensor([[True, False, False],
#         [False, True, False], 
#         [False, False, True]])

tensor1 = torch.tensor([5+0j, 0+0j, 3+0j])
tensor2 = torch.tensor([[True, False, True],
                        [False, True, False],
                        [True, False, True]])
torch.eq(input=tensor1, other=tensor2)
torch.eq(input=tensor2, other=tensor1)
# tensor([[False, True, False],
#         [False, False, False],
#         [False, True, False]])

tensor1 = torch.tensor([[5, 0, 3], [6, 9, 1]])
tensor2 = torch.tensor([[[2, 7, 3], [6, 3, 1]],
                        [[5, 0, 4], [8, 9, 7]]])
torch.eq(input=tensor1, other=tensor2)
torch.eq(input=tensor2, other=tensor1)
# tensor([[[False, False, True], [True, False, True]],
#         [[True, True, False], [False, True, False]]])

torch.eq(input=tensor1, other=3)
# tensor([[False, False, True], [False, False, False]])

torch.eq(input=tensor2, other=3)
# tensor([[[False, False, True], [False, True, False]],
#         [[False, False, False], [False, False, False]]])

ne() can check the zero or more elements of the 1st 0D or more D tensor are not equal to the zero or more elements of the 2nd 0D or more D tensor element-wise as shown below:

*Memos:

ne() can be used with torch or a tensor.
The 1st argument(tensor of int, float, complex or bool) with torch or using a tensor(tensor of int, float, complex or bool) is input(Required).
The 2nd argument(tensor of int, float, complex or bool or int, float, complex or bool) with torch or the 1st argument with a tensor(tensor of int, float, complex or bool or int, float, complex or bool) is other(Required).
The result is the higher D tensor which has more elements.
not_equal() is the alias of ne().

import torch

tensor1 = torch.tensor(5)
tensor2 = torch.tensor([[3, 5, 4],
                        [6, 3, 5]])
torch.ne(input=tensor1, other=tensor2)
tensor1.ne(other=tensor2)
torch.ne(input=tensor2, other=tensor1)
tensor2.ne(other=tensor1)
# tensor([[True, False, True],
          [True, True, False]])

torch.ne(input=tensor1, other=3)
# tensor(True)

torch.ne(input=tensor2, other=3)
# tensor([[False, True, True],
#         [True, False, True]])

tensor1 = torch.tensor([[5, 0, 3]])
tensor2 = torch.tensor([[5, 5, 5],
                        [0, 0, 0],
                        [3, 3, 3]])
torch.ne(input=tensor1, other=tensor2)
torch.ne(input=tensor2, other=tensor1)
# tensor([[False, True, True],
#         [True, False, True],
#         [True, True, False]])

torch.ne(input=tensor1, other=3)
torch.ne(input=tensor1, other=3.)
torch.ne(input=tensor1, other=3+0j)
# tensor([True, True, False])

torch.ne(input=tensor1, other=False)
# tensor([[True, False, True]])

torch.ne(input=tensor2, other=3)
torch.ne(input=tensor2, other=3.)
torch.ne(input=tensor2, other=3+0j)
# tensor([[True, True, True],
#         [True, True, True],
#         [False, False, False]])

torch.ne(input=tensor2, other=False)
# tensor([[True, True, True],
#         [False, False, False],
#         [True, True, True]])

tensor1 = torch.tensor([5., 0., 3.])
tensor2 = torch.tensor([[5+0j, 5+0j, 5+0j],
                        [0+0j, 0+0j, 0+0j],
                        [3+0j, 3+0j, 3+0j]])
torch.ne(input=tensor1, other=tensor2)
torch.ne(input=tensor2, other=tensor1)
# tensor([[False, True, True],
#         [True, False, True],
#         [True, True, False]])

tensor1 = torch.tensor([5+0j, 0+0j, 3+0j])
tensor2 = torch.tensor([[True, False, True],
                        [False, True, False],
                        [True, False, True]])
torch.ne(input=tensor1, other=tensor2)
torch.ne(input=tensor2, other=tensor1)
# tensor([[True, False, True],
#         [True, True, True],
#         [True, False, True]])

tensor1 = torch.tensor([[5, 0, 3], [6, 9, 1]])
tensor2 = torch.tensor([[[2, 7, 3], [6, 3, 1]],
                        [[5, 0, 4], [8, 9, 7]]])
torch.ne(input=tensor1, other=tensor2)
torch.ne(input=tensor2, other=tensor1)
# tensor([[[True, True, False], [False, True, False]],
#         [[False, False, True], [True, False, True]]])

torch.ne(input=tensor1, other=3)
# tensor([[True, True, False], [True, True, True]])

torch.ne(input=tensor2, other=3)
# tensor([[[True, True, False], [True, False, True]],
#         [[True, True, True], [True, True, True]]])

DEV Community

equal(), eq() and ne() in PyTorch

Top comments (0)

Read next

What’s the Best Programming Language to Learn First? It Depends

Tell us about your first step in your coding journey✈

9 Tips to Correctly Understand and Configure IAM on GCP

Spring Boot with Thymeleaf and Bootstrap