tf.keras.ops.pad

Pad a tensor.

tf.keras.ops.pad(
    x, pad_width, mode='constant', constant_values=None
)

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 = pad width 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 and mode != "constant".

Torch backend only supports modes "constant", "reflect", "symmetric" and "circular". Only Torch backend supports "circular" mode.

Tensorflow backend only supports modes "constant", "reflect" and "symmetric".

Padded tensor.