QBoard » Artificial Intelligence & ML » AI and ML - PyTorch » Pytorch reshape tensor dimension
User Dashboard

Pytorch reshape tensor dimension

Back To Topics
Tags : python pytorch tensor numpy deep-learning
  • 102 9

    For example, I have 1D vector with dimension (5). I would like to reshape it into 2D matrix (1,5).

    Here is how I do it with numpy

    >>> import numpy as np
>>> a = np.array([1,2,3,4,5])
>>> a.shape
(5,)
>>> a = np.reshape(a, (1,5))
>>> a.shape
(1, 5)
>>> a
array([[1, 2, 3, 4, 5]])
>>>

    But how can I do that with Pytorch Tensor (and Variable). I don't want to switch back to numpy and switch to Torch variable again, because it will loss backpropagation information.

    Here is what I have in Pytorch

    >>> import torch
>>> from torch.autograd import Variable
>>> a = torch.Tensor([1,2,3,4,5])
>>> a

 1
 2
 3
 4
 5
[torch.FloatTensor of size 5]

>>> a.size()
(5L,)
>>> a_var = variable(a)
>>> a_var = Variable(a)
>>> a_var.size()
(5L,)
.....do some calculation in forward function
>>> a_var.size()
(5L,)

    Now I want it size to be (1, 5). How can I resize or reshape the dimension of pytorch tensor in Variable without loss grad information. (because I will feed into another model before backward)

     
      September 17, 2020 2:44 PM IST
    0
  • 129 8

    Use torch.unsqueeze(input, dim, out=None)

    >>> import torch
>>> a = torch.Tensor([1,2,3,4,5])
>>> a

 1
 2
 3
 4
 5
[torch.FloatTensor of size 5]

>>> a = a.unsqueeze(0)
>>> a

 1  2  3  4  5
[torch.FloatTensor of size 1x5]
     
      September 17, 2020 5:35 PM IST
    0
  • 67 3

    you might use

    a.view(1,5)
Out: 

 1  2  3  4  5
[torch.FloatTensor of size 1x5]
      September 17, 2020 5:36 PM IST
    0
  • 106 5

    you can use this, the '-1' means you don't have to specify the number of the elements.

    In [3]: a.view(1,-1)
Out[3]:

 1  2  3  4  5
[torch.FloatTensor of size 1x5]
      September 17, 2020 5:37 PM IST
    0
  • 90 6 
    import torch
>>>a = torch.Tensor([1,2,3,4,5])
>>>a.size()
torch.Size([5])
#use view to reshape

>>>b = a.view(1,a.shape[0])
>>>b
tensor([[1., 2., 3., 4., 5.]])
>>>b.size()
torch.Size([1, 5])
>>>b.type()
'torch.FloatTensor'
      September 17, 2020 5:38 PM IST
    0
  • 461
    For in-place modification of the shape of the tensor, you should use tensor.resize_():
    In [23]: a = torch.Tensor([1, 2, 3, 4, 5])

In [24]: a.shape
Out[24]: torch.Size([5])


# tensor.resize_((`new_shape`))    
In [25]: a.resize_((1,5))
Out[25]: 

 1  2  3  4  5
[torch.FloatTensor of size 1x5]

In [26]: a.shape
Out[26]: torch.Size([1, 5])

     

    In PyTorch, if there's an underscore at the end of an operation (like tensor.resize_()) then that operation does in-place modification to the original tensor.

    Also, you can simply use np.newaxis in a torch Tensor to increase the dimension. Here is an example:

    In [34]: list_ = range(5)
In [35]: a = torch.Tensor(list_)
In [36]: a.shape
Out[36]: torch.Size([5])

In [37]: new_a = a[np.newaxis, :]
In [38]: new_a.shape
Out[38]: torch.Size([1, 5])
      September 17, 2020 5:41 PM IST
    0
  • 84 
    import torch
t = torch.ones((2, 3, 4))
t.size()

    >>torch.Size([2, 3, 4])

    a = t.view(-1,t.size()[1]*t.size()[2])
a.size()

    >>torch.Size([2, 12])
      December 22, 2020 2:59 PM IST
    0