*Memos:

My post explains aminmax(), amin() and amax().
My post explains minimum(), maximum(). fmin() and fmax().
My post explains kthvalue() and topk().

min() can get the one or more minimum elements of a 0D or more D tensor from one or two of 0D or more D tensors as shown below:

*Memos:

min() can be used with torch or a tensor.
The 1st argument(tensor of int, float or bool) with torch or using a tensor(tensor of int, float or bool) is input(Required).
The 2nd argument(int) with torch or the 1st argument(int) is dim(Optional). *Setting dim can get one or more 1st minimum elements and the indices of them.
The 2nd argument(tensor of int, float or bool) with torch or the 1st argument(tensor of int, float or bool) is other(Optional). *Memos:
- It can only be used with input.
- This is the functionality of minimum().
The 3rd argument(bool) with torch or the 2nd argument(bool) is keepdim(Optional). *Memos:
- It keeps the dimension of the input tensor.
- It must be used with dim.

import torch

my_tensor = torch.tensor([[5, 4, 7, 7],
                          [6, 5, 3, 5],
                          [3, 8, 9, 3]])
torch.min(input=my_tensor)
my_tensor.min()
# tensor(3)

torch.min(input=my_tensor, dim=0)
torch.min(input=my_tensor, dim=-2)
# torch.return_types.min(
# values=tensor([3, 4, 3, 3]),
# indices=tensor([2, 0, 1, 2]))

torch.min(input=my_tensor, dim=1)
torch.min(input=my_tensor, dim=-1)
# torch.return_types.min(
# values=tensor([4, 3, 3]),
# indices=tensor([1, 2, 0]))

torch.min(input=my_tensor, dim=0, keepdim=True)
# torch.return_types.min(
# values=tensor([[3, 4, 3, 3]]),
# indices=tensor([[2, 0, 1, 2]]))

tensor1 = torch.tensor([5, 4, 7, 7])
tensor2 = torch.tensor([[6, 5, 3, 5],
                        [3, 8, 9, 3]])
torch.min(input=tensor1, other=tensor2)
# tensor([[5, 4, 3, 5],
#         [3, 4, 7, 3]])

tensor1 = torch.tensor([5., 4., 7., 7.])
tensor2 = torch.tensor([[6., 5., 3., 5.],
                        [3., 8., 9., 3.]])
torch.min(input=tensor1, other=tensor2)
# tensor([[5., 4., 3., 5.],
#         [3., 4., 7., 3.]])

tensor1 = torch.tensor([True, False, True, False])
tensor2 = torch.tensor([[True, False, True, False],
                        [False, True, False, True]])
torch.min(input=tensor1, other=tensor2)
# tensor([[True, False, True, False],
#         [False, False, False, False]])

max() can get the one or more maximum elements of a 0D or more D tensor from one or two of 0D or more D tensors as shown below:

The 1st argument(tensor of int, float or bool) with torch or using a tensor(tensor of int, float or bool) is input(Required).
The 2nd argument(int or tuple of int) with torch or the 1st argument(int or tuple of int) is dim(Optional). *Setting dim can get one or more 1st maximum elements and the indices of them.
The 2nd argument(tensor of int, float or bool) with torch or the 1st argument(tensor of int, float or bool) is other(Optional). *Memos:
- It can only be used with input.
- This is the functionality of maximum().
The 3rd argument(bool) with torch or the 2nd argument(bool) is keepdim(Optional). *Memos:
- It keeps the dimension of the input tensor.
- It must be used with dim.

import torch

my_tensor = torch.tensor([[5, 4, 7, 7],
                          [6, 5, 3, 5],
                          [3, 8, 9, 3]])
torch.max(input=my_tensor)
my_tensor.max()
# tensor(9)

torch.max(input=my_tensor, dim=0)
torch.max(input=my_tensor, dim=-2)
# torch.return_types.max(
# values=tensor([6, 8, 9, 7]),
# indices=tensor([1, 2, 2, 0]))

torch.max(input=my_tensor, dim=1)
torch.max(input=my_tensor, dim=-1)
# torch.return_types.max(
# values=tensor([7, 6, 9]),
# indices=tensor([2, 0, 2]))

torch.max(input=my_tensor, dim=0, keepdim=True)
# torch.return_types.max(
# values=tensor([[6, 8, 9, 7]]),
# indices=tensor([[1, 2, 2, 0]]))

tensor1 = torch.tensor([5, 4, 7, 7])
tensor2 = torch.tensor([[6, 5, 3, 5],
                        [3, 8, 9, 3]])
torch.max(input=tensor1, other=tensor2)
# tensor([[6, 5, 7, 7],
#         [5, 8, 9, 7]])

tensor1 = torch.tensor([5., 4., 7., 7.])
tensor2 = torch.tensor([[6., 5., 3., 5.],
                        [3., 8., 9., 3.]])
torch.max(input=tensor1, other=tensor2)
# tensor([[6., 5., 7., 7.],
#         [5., 8., 9., 7.]])

tensor1 = torch.tensor([True, False, True, False])
tensor2 = torch.tensor([[True, False, True, False],
                        [False, True, False, True]])
torch.max(input=tensor1, other=tensor2)
# tensor([[True, False, True, False],
#         [True, True, True, True]])

argmin() can get the one or more indices of the 1st minimum elements of a 0D or more D tensor from a 0D or more D tensor as shown below:

*Memos:

argmin() can be used with torch or a tensor.
The 1st argument(tensor of int or float) with torch or using a tensor(tensor of int or float) is input(Required).
The 2nd argument(int) with torch or the 1st argument(int) is dim(Optional). *Setting dim can get the one or more indices of the 1st minimum elements.
One complex number or boolean value of a 1D or more D tensor with dim= works.

import torch

my_tensor = torch.tensor([[5, 4, 7, 7],
                          [6, 5, 3, 5],
                          [3, 8, 9, 3]])
torch.argmin(input=my_tensor)
my_tensor.argmin()
# tensor(6)

torch.argmin(input=my_tensor, dim=0)
torch.argmin(input=my_tensor, dim=-2)
# tensor([2, 0, 1, 2])

torch.argmin(input=my_tensor, dim=1)
torch.argmin(input=my_tensor, dim=-1)
# tensor([1, 2, 0])

torch.argmin(input=my_tensor, keepdim=True)
# tensor([[6]])

torch.argmin(input=my_tensor, dim=0, keepdim=True)
# tensor([[2, 0, 1, 2]])

my_tensor = torch.tensor([[5., 4., 7., 7.],
                          [6., 5., 3., 5.],
                          [3., 8., 9., 3.]])
torch.argmin(input=my_tensor)
# tensor(6)

my_tensor = torch.tensor([5+7j])

torch.argmin(input=my_tensor, dim=0)
torch.argmin(input=my_tensor, dim=-1)
# tensor(0)

my_tensor = torch.tensor([[True]])

torch.argmin(input=my_tensor, dim=0)
torch.argmin(input=my_tensor, dim=-1)
# tensor([0])

argmax() can get the indices of the 1st maximum elements of a 0D or more D tensor from a 0D or more D tensor as shown below:

*Memos:

argmax() can be called both from torch and a tensor.
The 1st argument(tensor of int or float) with torch or using a tensor(tensor of int or float) is input(Required).
The 2nd argument(int) with torch or the 1st argument(int) is dim(Optional). *Setting dim can get the one or more indices of the 1st maximum elements.
One complex number or boolean value of a 1D or more D tensor with dim= works.

import torch

my_tensor = torch.tensor([[5, 4, 7, 7],
                          [6, 5, 3, 5],
                          [3, 8, 9, 3]])
torch.argmax(input=my_tensor)
my_tensor.argmax()
# tensor(10)

torch.argmax(input=my_tensor, dim=0)
torch.argmax(input=my_tensor, dim=-2)
# tensor([1, 2, 2, 0])

torch.argmax(input=my_tensor, dim=1)
torch.argmax(input=my_tensor, dim=-1)
# tensor([2, 0, 2])

torch.argmax(input=my_tensor, keepdim=True)
# tensor([[10]])

torch.argmax(input=my_tensor, dim=0, keepdim=True)
# tensor([[1, 2, 2, 0]])

my_tensor = torch.tensor([[5., 4., 7., 7.],
                          [6., 5., 3., 5.],
                          [3., 8., 9., 3.]])
torch.argmax(input=my_tensor)
# tensor(10)

my_tensor = torch.tensor([5+7j])

torch.argmax(input=my_tensor, dim=0)
torch.argmax(input=my_tensor, dim=-1)
# tensor(0)

my_tensor = torch.tensor([[True]])

torch.argmax(input=my_tensor, dim=0)
torch.argmax(input=my_tensor, dim=-1)
# tensor([0])

min(), max(), argmin() and argmax() in PyTorch