tfg.image.pyramid.merge

Merges the different levels of the pyramid back to an image.

tfg.image.pyramid.merge(
    levels: List[type_alias.TensorLike], name: str = 'pyramid_merge'
) -> tf.Tensor

Args
`levels`	A list containing tensors of shape `[B, H_i, W_i, C]`, where `B` is the batch size, H_i and W_i are the height and width of the image for the level i, and `C` the number of channels of the image.
`name`	A name for this op that defaults to "pyramid_merge".

Returns
A tensor of shape `[B, H, W, C]`, where `B` is the batch size, `H` the height of the image, `W` the width of the image, and `C` the number of channels of the image.

Raises
`ValueError`	If the shape of the elements of `levels` is not supported.

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 2022-10-28 UTC.

Args