DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on • Edited on

flipud and fliplr in PyTorch

#python #pytorch #flipud #fliplr

Buy Me a Coffee☕

*My post explains flip().

flipud() can get the 1D or more D tensor of the zero or more elements reversed in the up/down direction from the 1D or more D tensor of zero or more elements as shown below:

*Memos:

  • flipud() can be used with torch or a tensor.
  • The 1st argument(input) with torch or using a tensor(Required-Type:tensor of int, float, complex or bool). 
import torch my_tensor = torch.tensor([2, 7, 4]) # 1D tensor  torch.flipud(input=my_tensor) my_tensor.flipud() # tensor([4, 7, 2])  my_tensor = torch.tensor([[2, 7, 4], [8, 3, 2]]) # 2D tensor  torch.flipud(input=my_tensor) # tensor([[8, 3, 2], [2, 7, 4]])  my_tensor = torch.tensor([[[2, 7, 4], [8, 3, 2]], # 3D tensor  [[5, 0, 8], [3, 6, 1]]]) torch.flipud(input=my_tensor) # tensor([[[5, 0, 8], [3, 6, 1]], # [[2, 7, 4], [8, 3, 2]]])  my_tensor = torch.tensor([[[2., 7., 4.], [8., 3., 2.]], # 3D tensor  [[5., 0., 8.], [3., 6., 1.]]]) torch.flipud(input=my_tensor) # tensor([[[5., 0., 8.], [3., 6., 1.]], # [[2., 7., 4.], [8., 3., 2.]]])  my_tensor = torch.tensor([[[2.+0.j, 7.+0.j, 4.+0.j], # 3D tensor  [8.+0.j, 3.+0.j, 2.+0.j]], [[5.+0.j, 0.+0.j, 8.+0.j], [3.+0.j, 6.+0.j, 1.+0.j]]]) torch.flipud(input=my_tensor) # tensor([[[5.+0.j, 0.+0.j, 8.+0.j], # [3.+0.j, 6.+0.j, 1.+0.j]], # [[2.+0.j, 7.+0.j, 4.+0.j], # [8.+0.j, 3.+0.j, 2.+0.j]]])  # 3D tensor my_tensor = torch.tensor([[[True, False, True], [True, False, True]], [[False, True, False], [False, True, False]]]) torch.flipud(input=my_tensor) # tensor([[[False, True, False], [False, True, False]], # [[True, False, True], [True, False, True]]])
Enter fullscreen mode Exit fullscreen mode

fliplr() can get the 2D or more D tensor of the zero or more elements reversed in the left/right direction from the 2D or more D tensor of zero or more elements as shown below:

*Memos:

  • fliplr() can be used with torch or a tensor.
  • The 1st argument(input) with torch or using a tensor(Required-Type:tensor of int, float, complex or bool). 
import torch my_tensor = torch.tensor([[2, 7, 4], [8, 3, 2]]) # 2D tensor  torch.fliplr(input=my_tensor) my_tensor.fliplr() # tensor([[4, 7, 2], [2, 3, 8]])  my_tensor = torch.tensor([[[2, 7, 4], [8, 3, 2]], # 3D tensor  [[5, 0, 8], [3, 6, 1]]]) torch.fliplr(input=my_tensor) # tensor([[[8, 3, 2], [2, 7, 4]], # [[3, 6, 1], [5, 0, 8]]])  my_tensor = torch.tensor([[[2., 7., 4.], [8., 3., 2.]], # 3D tensor  [[5., 0., 8.], [3., 6., 1.]]]) torch.fliplr(input=my_tensor) # tensor([[[8., 3., 2.], [2., 7., 4.]], # [[3., 6., 1.], [5., 0., 8.]]])  my_tensor = torch.tensor([[[2.+0.j, 7.+0.j, 4.+0.j], # 3D tensor  [8.+0.j, 3.+0.j, 2.+0.j]], [[5.+0.j, 0.+0.j, 8.+0.j], [3.+0.j, 6.+0.j, 1.+0.j]]]) torch.fliplr(input=my_tensor) # tensor([[[8.+0.j, 3.+0.j, 2.+0.j], # [2.+0.j, 7.+0.j, 4.+0.j]], # [[3.+0.j, 6.+0.j, 1.+0.j], # [5.+0.j, 0.+0.j, 8.+0.j]]])  # 3D tensor my_tensor = torch.tensor([[[True, False, True], [True, False, True]], [[False, True, False], [False, True, False]]]) torch.fliplr(input=my_tensor) # tensor([[[True, False, True], [True, False, True]], # [[False, True, False], [False, True, False]]])
Enter fullscreen mode Exit fullscreen mode

Top comments (0)