"reflect" padding used in Gaussian Blur Transform throws error on smaller images

[themurtazanazir]

🐛 Describe the bug

Because of the set reflect mode in torch_pad, the GaussianBlur throws exception for smaller images.

from PIL import Image
import numpy as np
from torchvision import transforms

im  = Image.new("L", (1, 1), 255)
transforms.GaussianBlur(3, sigma=(0.1, 4.0))(im)

We should either have a parameter to set the padding mode or 'reflect' should not be used when image size is smaller than kernel size.

Thanks.

Versions

PyTorch version: 1.12.1+cu102
Is debug build: False
CUDA used to build PyTorch: 10.2
ROCM used to build PyTorch: N/A

OS: Ubuntu 20.04.5 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.31

Python version: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0] (64-bit runtime)
Python platform: Linux-5.15.0-1020-aws-x86_64-with-glibc2.17
Is CUDA available: True
CUDA runtime version: Could not collect
GPU models and configuration: GPU 0: Tesla T4
Nvidia driver version: 515.65.01
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

Versions of relevant libraries:
[pip3] numpy==1.23.3
[pip3] torch==1.12.1
[pip3] torch-summary==1.4.5
[pip3] torchvision==0.13.1
[conda] numpy 1.23.3 pypi_0 pypi
[conda] torch 1.12.1 pypi_0 pypi
[conda] torch-summary 1.4.5 pypi_0 pypi
[conda] torchvision 0.13.1 pypi_0 pypi

cc @vfdev-5 @datumbox