Assigning values to torch tensors

Question

I'm trying to assign some values to a torch tensor. In the sample code below, I initialized a tensor U and try to assign a tensor b to its last 2 dimensions. In reality, this is a loop over i and j that solves some relation for a number of training data (here 10) and assigns it to its corresponding location.

import torch

U = torch.zeros([10, 1, 4, 4])
b = torch.rand([10, 1, 1, 1])

i = 2
j = 2
U[:, :, i, j] = b

I was expecting vector b to be assigned for dimensions i and j of corresponding training data (shape of training data being (10,1)) but it gives me an error. The error that I get is the following

RuntimeError: expand(torch.FloatTensor{[10, 1, 1, 1]}, size=[10, 1]): the number of sizes provided (2) must be greater or equal to the number of dimensions in the tensor (4)

Any suggestions on how to fix it would be appreciated.

As an example, you can think of this as if '[10, 1]' is the shape of my data. Imagine it is 10 images, each of which has one channel. Then imagine each image is of shape '[4, 4]'. In each iteration of the loop, pixel '[i, j]' for all images and channels is being calculated.

Khoyo · Accepted Answer · 2019-06-03 22:11:46Z

3

Your b tensor has too much dimensions.

U[:, :, i, j] has a [10, 1] shape (try U[:, :, i, j].shape)

Use b = torch.rand([10, 1]) instead.

answered Jun 3, 2019 at 22:11

Khoyo

1,24713 silver badges21 bronze badges

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

1 Comment

Blade Over a year ago

You are right, I think using squeeze would be the best way to reshape my b tensor to fix the issue (as I don't define tensor b myself in the actual code) and reduce dimensions.

Blade · Accepted Answer · 2019-06-04 16:53:17Z

1

Thanks to @Khoyo's tip on the source of the problem, I used reshape to fix this as following

import torch

U = torch.zeros([10, 1, 4, 4])
b = torch.rand([10, 1, 1, 1])

i = 2
j = 2
U[:, :, i, j] = b.reshape((-1))

answered Jun 4, 2019 at 16:53

Blade

1,1403 gold badges19 silver badges45 bronze badges

Comments

alireza dizaji · Accepted Answer · 2022-04-04 11:24:06Z

0

there is a shape mismatch in your assignment. U[..., [i], [j]] will do the same meanwhile keep the last two dimensions for you.

answered Apr 4, 2022 at 11:24

alireza dizaji

113 bronze badges

Collectives™ on Stack Overflow

Assigning values to torch tensors

3 Answers 3

1 Comment

Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

3 Answers 3

1 Comment

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related