tf.keras.ops.dsplit

Split an array into multiple sub-arrays depth-wise.

tf.keras.ops.dsplit(
    x, indices_or_sections
)

x Input tensor.
indices_or_sections If an integer, N, the tensor will be split into N equal sections along axis 2. If a 1-D array of sorted integers, the entries indicate indices at which the tensor will be split along axis 2.

A list of sub-arrays.

Example:

x = keras.ops.arange(16.0).reshape((2, 2, 4))
keras.ops.dsplit(x, 2)
[array([[[ 0.,  1.],
        [ 4.,  5.]],
       [[ 8.,  9.],
        [12., 13.]]]),
 array([[[ 2.,  3.],
        [ 6.,  7.]],
       [[10., 11.],
        [14., 15.]]])]