Menu
What is the difference between tensor.permute() and tensor.view()?
They seem to do the same thing.
978
permute() method is used to perform a permute operation on a PyTorch tensor. It returns a view of the input tensor with its dimension permuted. It doesn't make a copy of the original tensor. For example, a tensor with dimension [2, 3] can be permuted to [3, 2].
transpose() and permute() Note that, in permute() , you must provide the new order of all the dimensions. In transpose() , you can only provide two dimensions.
PyTorch allows a tensor to be a View of an existing tensor. View tensor shares the same underlying data with its base tensor. Supporting View avoids explicit data copy, thus allows us to do fast and memory efficient reshaping, slicing and element-wise operations.
Returns a tensor that is a transposed version of input . The given dimensions dim0 and dim1 are swapped. If input is a strided tensor then the resulting out tensor shares its underlying storage with the input tensor, so changing the content of one would change the content of the other.
In [12]: aten = torch.tensor([[1, 2, 3], [4, 5, 6]]) In [13]: aten Out[13]: tensor([[ 1, 2, 3], [ 4, 5, 6]]) In [14]: aten.shape Out[14]: torch.Size([2, 3]) torch.view() reshapes the tensor to a different but compatible shape. For example, our input tensor aten has the shape (2, 3). This can be viewed as tensors of shapes (6, 1), (1, 6) etc.,
# reshaping (or viewing) 2x3 matrix as a column vector of shape 6x1 In [15]: aten.view(6, -1) Out[15]: tensor([[ 1], [ 2], [ 3], [ 4], [ 5], [ 6]]) In [16]: aten.view(6, -1).shape Out[16]: torch.Size([6, 1]) Alternatively, it can also be reshaped or viewed as a row vector of shape (1, 6) as in:
In [19]: aten.view(-1, 6) Out[19]: tensor([[ 1, 2, 3, 4, 5, 6]]) In [20]: aten.view(-1, 6).shape Out[20]: torch.Size([1, 6]) Whereas tensor.permute() is only used to swap the axes. The below example will make things clear:
In [39]: aten Out[39]: tensor([[ 1, 2, 3], [ 4, 5, 6]]) In [40]: aten.shape Out[40]: torch.Size([2, 3]) # swapping the axes/dimensions 0 and 1 In [41]: aten.permute(1, 0) Out[41]: tensor([[ 1, 4], [ 2, 5], [ 3, 6]]) # since we permute the axes/dims, the shape changed from (2, 3) => (3, 2) In [42]: aten.permute(1, 0).shape Out[42]: torch.Size([3, 2]) You can also use negative indexing to do the same thing as in:
In [45]: aten.permute(-1, 0) Out[45]: tensor([[ 1, 4], [ 2, 5], [ 3, 6]]) In [46]: aten.permute(-1, 0).shape Out[46]: torch.Size([3, 2]) View changes how the tensor is represented. For ex: a tensor with 4 elements can be represented as 4X1 or 2X2 or 1X4 but permute changes the axes. While permuting the data is moved but with view data is not moved but just reinterpreted.
Below code examples may help you. a is 2x2 tensor/matrix. With the use of view you can read a as a column or row vector (tensor). But you can't transpose it. To transpose you need permute. Transpose is achieved by swapping/permuting axes.
In [7]: import torch In [8]: a = torch.tensor([[1,2],[3,4]]) In [9]: a Out[9]: tensor([[ 1, 2], [ 3, 4]]) In [11]: a.permute(1,0) Out[11]: tensor([[ 1, 3], [ 2, 4]]) In [12]: a.view(4,1) Out[12]: tensor([[ 1], [ 2], [ 3], [ 4]]) In [13]: Bonus: See https://twitter.com/karpathy/status/1013322763790999552
23
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
