tfm.vision.augment.translate

Translates image(s) by provided vectors.

image An image Tensor of type uint8.
translations A vector or matrix representing [dx dy].
fill_value a float represents the value to be filled outside the boundaries when fill_mode="constant".
fill_mode Points outside the boundaries of the input are filled according to the given mode (one of {"constant", "reflect", "wrap", "nearest"}).
interpolation Interpolation mode. Supported values: "nearest", "bilinear".

The translated version of the image.