tf.keras.ops.pad  |  TensorFlow v2.16.1 (original) (raw)

tf.keras.ops.pad

Pad a tensor.

View aliases

Main aliases

tf.keras.ops.numpy.pad

tf.keras.ops.pad(
    x, pad_width, mode='constant', constant_values=None
)
Args
x Tensor to pad.
pad_width Number of values padded to the edges of each axis.((before_1, after_1), ...(before_N, after_N)) unique pad widths for each axis.((before, after),) yields same before and after pad for each axis.(pad,) or int is a shortcut for before = after = padwidth for all axes.
mode One of "constant", "edge", "linear_ramp","maximum", "mean", "median", "minimum","reflect", "symmetric", "wrap", "empty","circular". Defaults to"constant".
constant_values value to pad with if mode == "constant". Defaults to 0. A ValueError is raised if not None andmode != "constant".
Note
Torch backend only supports modes "constant", "reflect","symmetric" and "circular". Only Torch backend supports "circular" mode.
Note
Tensorflow backend only supports modes "constant", "reflect"and "symmetric".
Returns
Padded 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. Some content is licensed under the numpy license.

Last updated 2024-06-07 UTC.