tf.keras.ops.meshgrid

Creates grids of coordinates from coordinate vectors.

tf.keras.ops.meshgrid(
    *x, indexing='xy'
)

Given N 1-D tensors T0, T1, ..., TN-1 as inputs with corresponding lengths S0, S1, ..., SN-1, this creates an N N-dimensional tensors G0, G1, ..., GN-1 each with shape (S0, ..., SN-1) where the output Gi is constructed by expanding Ti to the result shape.

x 1-D tensors representing the coordinates of a grid.
indexing "xy" or "ij". "xy" is cartesian; "ij" is matrix indexing of output. Defaults to "xy".

Sequence of N tensors.

Example:

from keras.src import ops
x = ops.array([1, 2, 3])
y = ops.array([4, 5, 6])

grid_x, grid_y = ops.meshgrid(x, y, indexing="ij")
grid_x
array([[1, 1, 1],
       [2, 2, 2],
       [3, 3, 3]])
grid_y
array([[4, 5, 6],
       [4, 5, 6],
       [4, 5, 6]])