tfio.experimental.filter.gaussian

Apply Gaussian filter to image.

tfio.experimental.filter.gaussian(
    input, ksize, sigma, mode=None, constant_values=None, name=None
)

Args
`input`	A 4-D (`[N, H, W, C]`) Tensor.
`ksize`	A scalar or 1-D `[kx, ky]` Tensor. Size of the Gaussian kernel. If scalar, then `ksize` will be broadcasted to 1-D `[kx, ky]`.
`sigma`	A scalar or 1-D `[sx, sy]` Tensor. Standard deviation for Gaussian kernel. If scalar, then `sigma` will be broadcasted to 1-D `[sx, sy]`.
`mode`	A `string`. One of "CONSTANT", "REFLECT", or "SYMMETRIC" (case-insensitive). Default "CONSTANT".
`constant_values`	A `scalar`, the pad value to use in "CONSTANT" padding mode. Must be same type as input. Default 0.
`name`	A name for the operation (optional).

Returns
A 4-D (`[N, H, W, C]`) Tensor.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2022-02-15 UTC.

Args