I am confused by this error. I have uploaded my own style images and used the supplie

<a target="_blank" rel="noopener noreferrer nofollow" href="https://user-images.github

The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0 about jojogan HOT 5 CLOSED

onzie9 commented on May 10, 2024

The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0

from jojogan.

Comments (5)

mchong6 commented on May 10, 2024

Only one style image is needed. This issue looks like when your style image is a png with 4 channels. The align face code seems to have issues with that. Can you paste the entire error you got so I know which line is causing this? Alternatively try another style image.

from jojogan.

onzie9 commented on May 10, 2024

Here is the full error. Note that img.shape from opencv indicates the image is 3 channel.

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-22-1fb6e2251d67> in <module>()
     18 for name in names:
     19     style_path = f'style_images_aligned/{strip_path_extension(name)}.png'
---> 20     style_image = transform(Image.open(style_path))
     21     style_images.append(style_image)
     22 

3 frames
/usr/local/lib/python3.7/dist-pack
![Screen Shot 2022-01-10 at 5 00 21 PM](https://user-images.githubusercontent.com/10655590/148787707-921bdd2b-edbc-49a7-92d3-050402671a78.png)
ages/torchvision/transforms/functional.py in normalize(tensor, mean, std, inplace)
    349     if std.ndim == 1:
    350         std = std.view(-1, 1, 1)
--> 351     tensor.sub_(mean).div_(std)
    352     return tensor
    353 

RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0

from jojogan.

onzie9 commented on May 10, 2024

from jojogan.

mchong6 commented on May 10, 2024

Try doing this

style_image = transform(Image.open(style_path).convert("RGB")

I actually am not sure why this is happening, I kind of assume that if the align face function worked, the resulting PNG image will always be 3 channels. Maybe that assumption is wrong.

from jojogan.

onzie9 commented on May 10, 2024

That did it! Thanks.

from jojogan.

Recommend Projects