Torchvision transforms ToTensor not working

data
1

I’m working with spectrograms, each image is 288 * 432. ToTensor() isn’t working for me, I believe it should have brought height and width of each one between 0 and 1.
Picture1
Can someone please help?
Thank you.

2

Hi,
Please refer to the docs and check whether your images do not fall into the cases when the image is returned without scaling. (range should be 0-255 etc.)

3

Thanks, I understand. What do you think is a good way to bring the resolution in [0-255]? RandomResizedCrop()? Or something else?

Thank you.

4

This is used to re-size the image (change the dimensionality) rather than to interfere with the pixel values.

As long as the pixel values are in the range 0-255 and the PIL image is in one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1), the scaling should work fine. See:

import numpy
from PIL import Image
import torch
import torchvision.transforms as transforms

imarray = numpy.random.rand(300, 300, 3) * 255
im = Image.fromarray(imarray.astype('uint8')).convert('RGB')

trans = transforms.ToTensor()
im_tens = trans(im)

im_tens = torch.where(im_tens>1.0, 1.0, 0.0)
print(im_tens.sum()) # tensor(0.)

You could use manual scaling in case your pixel values are outside 0-255.

1 Like
5

Thanks, Srishti. I was trying manual transformation. Wrote the following, not sure why it’s not working.

Picture1

Could you please have a look?

Thank you.

6

Hi,
Could you please post your code enclosed with three backticks ```.
Please also provide an example of what transformations you’d like to do with your images.