L1Loss() and MSELoss() in PyTorch

Buy Me a Coffee☕

*Memos:
My post explains L1 Loss(MAE), L2 Loss(MSE), Huber Loss, BCE and Cross Entropy Loss.

L1Loss() can get the 0D or more D tensor of the zero or more values(float) computed by L1Loss(MAE) from the 0D or more D tensor of zero or m…


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

Buy Me a Coffee☕

*Memos:
My post explains L1 Loss(MAE), L2 Loss(MSE), Huber Loss, BCE and Cross Entropy Loss.

L1Loss() can get the 0D or more D tensor of the zero or more values(float) computed by L1Loss(MAE) from the 0D or more D tensor of zero or more elements as shown below:

*Memos:

  • There is reduction argument for initialization(Optional-Default:'mean'-Type:str). *'none', 'mean' or 'sum' can be selected.
  • There are size_average and reduce argument for initialization but they are deprecated.
  • The 1st argument is input(Required-Type:tensor of float or complex).
  • The 2nd argument is target(Required-Type:tensor of float or complex).
  • input and target should be the same size otherwise there is sometimes a warning.
  • Even complex type of input and target tensors return a float tensor.
  • The empty 1D or more D input and target tensors with reduction='mean' return nan.
  • The empty 1D or more D input and target tensors with reduction='sum' return 0.. Image description 
import torch
from torch import nn

tensor1 = torch.tensor([ 8., -3., 0.,  1.,  5., -2., -1., 4.])
tensor2 = torch.tensor([-3.,  7., 4., -2., -9.,  6., -8., 5.])
                     #  11.+ 10.+ 4. + 3.+ 14. + 8. + 7.+ 1. = 58.
                     #  58. / 8 = 7.2500
l1loss = nn.L1Loss()
l1loss(input=tensor1, target=tensor2)
# tensor(7.2500)

l1loss
# L1Loss()

l1loss.reduction
# 'mean'

l1loss = nn.L1Loss(reduction='mean')
l1loss(input=tensor1, target=tensor2)
# tensor(7.2500)

l1loss = nn.L1Loss(reduction='sum')
l1loss(input=tensor1, target=tensor2)
# tensor(58.)

l1loss = nn.L1Loss(reduction='none')
l1loss(input=tensor1, target=tensor2)
# tensor([11., 10.,  4.,  3., 14.,  8.,  7.,  1.])

tensor1 = torch.tensor([[8., -3., 0., 1.], [5., -2., -1., 4.]])
tensor2 = torch.tensor([[-3., 7., 4., -2.], [-9., 6., -8., 5.]])

l1loss = nn.L1Loss()
l1loss(input=tensor1, target=tensor2)
# tensor(7.2500)

tensor1 = torch.tensor([[[8., -3.], [0., 1.]], [[5., -2.], [-1., 4.]]])
tensor2 = torch.tensor([[[-3., 7.], [4., -2.]], [[-9., 6.], [-8., 5.]]])

l1loss = nn.L1Loss()
l1loss(input=tensor1, target=tensor2)
# tensor(7.2500)

tensor1 = torch.tensor([[[8.+0.j, -3.+0.j], [0.+0.j, 1.+0.j]],
                        [[5.+0.j, -2.+0.j], [-1.+0.j, 4.+0.j]]])
tensor2 = torch.tensor([[[-3.+0.j, 7.+0.j], [4.+0.j, -2.+0.j]],
                        [[-9.+0.j, 6.+0.j], [-8.+0.j, 5.+0.j]]])
l1loss = nn.L1Loss()
l1loss(input=tensor1, target=tensor2)
# tensor(7.2500)

tensor1 = torch.tensor([])
tensor2 = torch.tensor([])

mseloss = nn.L1Loss(reduction='mean')
mseloss(input=tensor1, target=tensor2)
# tensor(nan)

mseloss = nn.L1Loss(reduction='sum')
mseloss(input=tensor1, target=tensor2)
# tensor(0.)

MSELoss() can get the 0D or more D tensor of the zero or more values(float) computed by L2Loss(MSE) from the 0D or more D tensor of zero or more elements as shown below:

*Memos:

  • There is reduction argument for initialization(Optional-Default:'mean'-Type:str). *'none', 'mean' or 'sum' can be selected.
  • There are size_average and reduce argument for initialization but they are deprecated.
  • The 1st argument is input(Required-Type:tensor of float).
  • The 2nd argument is target(Required-Type:tensor of float).
  • input and target should be the same size otherwise there is sometimes a warning.
  • The empty 1D or more D input and target tensors with reduction='mean' return nan.
  • The empty 1D or more D input and target tensors with reduction='sum' return 0.. Image description 
import torch
from torch import nn

tensor1 = torch.tensor([ 8., -3., 0.,  1.,  5., -2., -1., 4.])
tensor2 = torch.tensor([-3.,  7., 4., -2., -9.,  6., -8., 5.])
                     #  11. -10. -4.   3.  14.  -8.   7. -1.
                     #   ^2   ^2  ^2   ^2   ^2   ^2   ^2  ^2
                     # 121. 100. 16.   9. 196.  64.  49.  1. = 556.
                     # 556. / 8 = 69.5000
mseloss = nn.MSELoss()
mseloss(input=tensor1, target=tensor2)
# tensor(69.5000)

mseloss
# MSELoss()

mseloss.reduction
# 'mean'

mseloss = nn.MSELoss(reduction='mean')
mseloss(input=tensor1, target=tensor2)
# tensor(69.5000)

mseloss = nn.MSELoss(reduction='sum')
mseloss(input=tensor1, target=tensor2)
# tensor(556.)

mseloss = nn.MSELoss(reduction='none')
mseloss(input=tensor1, target=tensor2)
# tensor([121., 100., 16., 9., 196., 64., 49., 1.])

tensor1 = torch.tensor([[8., -3., 0., 1.], [5., -2., -1., 4.]])
tensor2 = torch.tensor([[-3., 7., 4., -2.], [-9., 6., -8., 5.]])

mseloss = nn.MSELoss()
mseloss(input=tensor1, target=tensor2)
# tensor(69.5000)

tensor1 = torch.tensor([[[8., -3.], [0., 1.]], [[5., -2.], [-1., 4.]]])
tensor2 = torch.tensor([[[-3., 7.], [4., -2.]], [[-9., 6.], [-8., 5.]]])

mseloss = nn.MSELoss()
mseloss(input=tensor1, target=tensor2)
# tensor(69.5000)

tensor1 = torch.tensor([])
tensor2 = torch.tensor([])

mseloss = nn.MSELoss(reduction='mean')
mseloss(input=tensor1, target=tensor2)
# tensor(nan)

mseloss = nn.MSELoss(reduction='sum')
mseloss(input=tensor1, target=tensor2)
# tensor(0.)


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 (2024-08-17T18:31:35+00:00) L1Loss() and MSELoss() in PyTorch. Retrieved from https://www.scien.cx/2024/08/17/l1loss-and-mseloss-in-pytorch/

MLA
" » L1Loss() and MSELoss() in PyTorch." Super Kai (Kazuya Ito) | Sciencx - Saturday August 17, 2024, https://www.scien.cx/2024/08/17/l1loss-and-mseloss-in-pytorch/
HARVARD
Super Kai (Kazuya Ito) | Sciencx Saturday August 17, 2024 » L1Loss() and MSELoss() in PyTorch., viewed ,<https://www.scien.cx/2024/08/17/l1loss-and-mseloss-in-pytorch/>
VANCOUVER
Super Kai (Kazuya Ito) | Sciencx - » L1Loss() and MSELoss() in PyTorch. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/08/17/l1loss-and-mseloss-in-pytorch/
CHICAGO
" » L1Loss() and MSELoss() in PyTorch." Super Kai (Kazuya Ito) | Sciencx - Accessed . https://www.scien.cx/2024/08/17/l1loss-and-mseloss-in-pytorch/
IEEE
" » L1Loss() and MSELoss() in PyTorch." Super Kai (Kazuya Ito) | Sciencx [Online]. Available: https://www.scien.cx/2024/08/17/l1loss-and-mseloss-in-pytorch/. [Accessed: ]
rf:citation
» L1Loss() and MSELoss() in PyTorch | Super Kai (Kazuya Ito) | Sciencx | https://www.scien.cx/2024/08/17/l1loss-and-mseloss-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