Resize PyTorch Tensor

Question

I am currently using the tensor.resize() function to resize a tensor to a new shape t = t.resize(1, 2, 3).

This gives me a deprecation warning:

non-inplace resize is deprecated

Hence, I wanted to switch over to the tensor.resize_() function, which seems to be the appropriate in-place replacement. However, this leaves me with an

cannot resize variables that require grad

error. I can fall back to

from torch.autograd._functions import Resize
Resize.apply(t, (1, 2, 3))

which is what tensor.resize() does in order to avoid the deprecation warning. This doesn't seem like an appropriate solution but rather a hack to me. How do I correctly make use of tensor.resize_() in this case?

Are you sure you want to use resize the tensor, not reshape? And if you want to resize it, is there anything you can archive with resize, what isn't possible by using slicing operations? — MBT
– MBT, Commented Jun 6, 2018 at 11:30
I think you have a point. Actually, now that you mention it I'm realizing that I probably should have used reshape in the first place. Here's the output of t.size() before and after the operation: torch.Size([16, 512, 8, 10, 2]) and torch.Size([16, 512, 8, 20]) — LL_
– LL_, Commented Jun 6, 2018 at 11:46
Yes, so I think you can just use view or reshape (from version 0.4.0). — MBT
– MBT, Commented Jun 6, 2018 at 11:51

kmario23 · Accepted Answer · 2020-04-21 12:44:27Z

13

You can instead choose to go with tensor.reshape(new_shape) or torch.reshape(tensor, new_shape) as in:

# a `Variable` tensor
In [15]: ten = torch.randn(6, requires_grad=True)

# this would throw RuntimeError error
In [16]: ten.resize_(2, 3)
---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-16-094491c46baa> in <module>()
----> 1 ten.resize_(2, 3)

RuntimeError: cannot resize variables that require grad

The above RuntimeError can be resolved or avoided by using tensor.reshape(new_shape)

In [17]: ten.reshape(2, 3)
Out[17]: 
tensor([[-0.2185, -0.6335, -0.0041],
        [-1.0147, -1.6359,  0.6965]])

# yet another way of changing tensor shape
In [18]: torch.reshape(ten, (2, 3))
Out[18]: 
tensor([[-0.2185, -0.6335, -0.0041],
        [-1.0147, -1.6359,  0.6965]])

edited Apr 21, 2020 at 12:44

answered Jun 6, 2018 at 12:10

kmario23

62.1k17 gold badges174 silver badges159 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

LL_ Over a year ago

As already noted by @blue-phoenox in the comments to the question, what I tried to achieve was indeed a reshape rather than a resize. I implemented the solution suggested here and it works just fine!

LL_ Over a year ago

As a side-note: I used the tensor.reshape() function due to its easier readability!

Antony Hatchkins · Accepted Answer · 2020-01-08 12:16:23Z

1

Please can you try something like:

import torch
x = torch.tensor([[1, 2], [3, 4], [5, 6]])
print(":::",x.resize_(2, 2))
print("::::",x.resize_(3, 3))

edited Jan 8, 2020 at 12:16

Antony Hatchkins

34.4k13 gold badges121 silver badges114 bronze badges

answered Jun 22, 2019 at 7:03

Sunil

1812 silver badges4 bronze badges

Comments

Daniel · Accepted Answer · 2018-06-06 14:08:04Z

0

Simply use t = t.contiguous().view(1, 2, 3) if you don't really want to change its data.

If not the case, the in-place resize_ operation will break the grad computation graph of t.
If it doesn't matter to you, just use t = t.data.resize_(1,2,3).

edited Jun 6, 2018 at 14:08

answered Jun 6, 2018 at 14:02

Daniel

2,3353 gold badges17 silver badges25 bronze badges

Collectives™ on Stack Overflow

Resize PyTorch Tensor

3 Answers 3

2 Comments

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

3 Answers 3

2 Comments

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related