tf.keras.ops.vsplit

Split an array into multiple sub-arrays vertically (row-wise).

View aliases

Main aliases

tf.keras.ops.numpy.vsplit

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

Args
x	Input tensor.
indices_or_sections	If an integer, N, the tensor will be split into N equal sections along axis 0. If a 1-D array of sorted integers, the entries indicate indices at which the tensor will be split along axis 0.

Returns
A list of sub-arrays.

Example:

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