GaussianBlur — Torchvision main documentation (2024)

Blurs image with randomly chosen Gaussian blur kernel.

The convolution will be using reflection padding corresponding to the kernel size, to maintain the input shape.

If the input is a Tensor, it is expectedto have […, C, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters:

• kernel_size (int or sequence) – Size of the Gaussian kernel.

  See Also

  CLIP STUDIO PAINT Instruction manualGaussian Filtering - Computer Vision Website HeaderImage Processing with Python: Blurring ImagesGaussian Blur Algorithm

• sigma (float or tuple of python:float (min, max)) – Standard deviation to be used forcreating kernel to perform blurring. If float, sigma is fixed. If it is tupleof float (min, max), sigma is chosen uniformly at random to lie in thegiven range.

Examples using GaussianBlur:

static get_params(sigma_min: float, sigma_max: float) → float[source]¶

Choose sigma for random gaussian blurring.

Parameters:

• sigma_min (float) – Minimum standard deviation that can be chosen for blurring kernel.

• sigma_max (float) – Maximum standard deviation that can be chosen for blurring kernel.

Returns:

Standard deviation to be passed to calculate kernel for gaussian blurring.

Return type:

float