PIL GaussianBlur vs tfv.gaussian_blur

vision
#1

Hi, I want to use torchvision’s gaussian_blur instead of PIL’s gaussian blur; in pil you have one sigma input; how can I translate that sigma into kernel_size and sigma of torchvision, also are the paddings the same?

It seems like an easy question but so far I couldn’t figure out the exact parameters even with visualization (btw, I only care about sigma when it’s between 0.1 and 2.0 (self-supervised data augmentation))
I also found this question on StackOverflow.

The reason I’m asking is that I used PIL to train a MoCov2 on imagenet for 35 epochs and it’s performing almost 2% (absolute) better than the one with torchvision

and yes, I’m using different blurs for different images of the minibatch, so the only difference is the blur function

#2

The question is more what is the (effective) kernel size for PIL’s GaussianBlur.
For any given radius, you can check experimentally:

img = torch.zeros(3, 20, 20)
img[:, 10, 10] = 1

img_pil = torchvision.transforms.functional.to_pil_image(img)
#?? torchvision.transforms.functional.gaussian_blur

img_blur_pil = img_pil.filter(PIL.ImageFilter.GaussianBlur(radius=2))
img_blur_pil_t = torchvision.transforms.functional.to_tensor(img_blur_pil)

print((img_blur_pil_t[0]>0).any(dim=1).sum())

img_blur = torchvision.transforms.functional.gaussian_blur(img, 11, 2)
print((img_blur[0]>0).any(dim=1).sum())

In general, this is a complex topic, the PIL Documentation references a 12-page article (Gwosdek et al: Theoretical Foundations of Gaussian Convolution by Extended Box Filtering) for their implementation accuracy.

Best regards

Thomas

1 Like