argmin() and argmax() in PyTorch

*Memos:

My post explains min() and max().

My post explains aminmax(), amin() and amax().

My post explains minimum(), maximum(). fmin() and fmax().

My post explains kthvalue() and topk().

argmin() can get the 0D or more D tensor of the zero or m…


This content originally appeared on DEV Community and was authored by Super Kai (Kazuya Ito)

*Memos:

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

*Memos:

  • argmin() can be used with torch or a tensor.
  • The 1st argument with torch or using a tensor is input(Required-Type:tensor of int or float).
  • The 2nd argument with torch or the 1st argument is dim(Optional-Type:int). *Setting dim can get the zero or more indices of the 1st minimum elements.
  • The 3rd argument with torch or the 2nd argument is keepdim(Optional-Type:bool). *My post explains keepdim argument.
  • The 1D or more D tensor of one complex number or boolean value with dim= works.
  • Empty 2D or more D input tensor without other tensor doesn't work if not setting dim.
  • Empty 1D input tesnor without other tensor doesn't work even if setting dim. 
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])

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.+7.j])

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

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

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

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

torch.argmin(input=my_tensor) # Error

my_tensor = torch.tensor([])

torch.argmin(input=my_tensor, dim=0) # Error

my_tensor = torch.tensor([[]])

torch.argmin(input=my_tensor, dim=0)
# tensor([], dtype=torch.int64)

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

torch.argmin(input=my_tensor, dim=0)
# tensor([], size=(1, 0), dtype=torch.int64)

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

*Memos:

  • argmax() can be used with torch or a tensor.
  • The 1st argument with torch or using a tensor is input(Required-Type:tensor of int or float).
  • The 2nd argument with torch or the 1st argument is dim(Optional-Type:int). *Setting dim can get the zero or more indices of the 1st maximum elements.
  • The 3rd argument with torch or the 2nd argument is keepdim(Optional-Type:bool). *My post explains keepdim argument.
  • The 1D or more D tensor of one complex number or boolean value with dim= works.
  • Empty 2D or more D input tensor without other tensor doesn't work if not setting dim.
  • Empty 1D input tesnor without other tensor doesn't work even if setting dim. 
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])

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.+7.j])

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

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

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

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

torch.argmax(input=my_tensor) # Error

my_tensor = torch.tensor([])

torch.argmax(input=my_tensor, dim=0) # Error

my_tensor = torch.tensor([[]])

torch.argmax(input=my_tensor, dim=0)
# tensor([], dtype=torch.int64)

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

torch.argmax(input=my_tensor, dim=0)
# tensor([], size=(1, 0), dtype=torch.int64)


This content originally appeared on DEV Community and was authored by Super Kai (Kazuya Ito)


Print Share Comment Cite Upload Translate Updates
APA

Super Kai (Kazuya Ito) | Sciencx (2024-07-04T17:27:30+00:00) argmin() and argmax() in PyTorch. Retrieved from https://www.scien.cx/2024/07/04/argmin-and-argmax-in-pytorch/

MLA
" » argmin() and argmax() in PyTorch." Super Kai (Kazuya Ito) | Sciencx - Thursday July 4, 2024, https://www.scien.cx/2024/07/04/argmin-and-argmax-in-pytorch/
HARVARD
Super Kai (Kazuya Ito) | Sciencx Thursday July 4, 2024 » argmin() and argmax() in PyTorch., viewed ,<https://www.scien.cx/2024/07/04/argmin-and-argmax-in-pytorch/>
VANCOUVER
Super Kai (Kazuya Ito) | Sciencx - » argmin() and argmax() in PyTorch. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/07/04/argmin-and-argmax-in-pytorch/
CHICAGO
" » argmin() and argmax() in PyTorch." Super Kai (Kazuya Ito) | Sciencx - Accessed . https://www.scien.cx/2024/07/04/argmin-and-argmax-in-pytorch/
IEEE
" » argmin() and argmax() in PyTorch." Super Kai (Kazuya Ito) | Sciencx [Online]. Available: https://www.scien.cx/2024/07/04/argmin-and-argmax-in-pytorch/. [Accessed: ]
rf:citation
» argmin() and argmax() in PyTorch | Super Kai (Kazuya Ito) | Sciencx | https://www.scien.cx/2024/07/04/argmin-and-argmax-in-pytorch/ |

Please log in to upload a file.



There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.

Related Posts