split

paddle.fluid.layers.split(input, num_or_sections, dim=-1, name=None)[source]

Split the input tensor into multiple sub-Tensors.

Parameters

  • input (Variable) – The input variable which is an N-D Tensor or LoDTensor, data type being float32, float64, int32 or int64.

  • num_or_sections (int|list|tuple) – If num_or_sections is an integer, then the integer indicates the number of equal sized sub-Tensors that the Tensor will be divided into. If num_or_sections is a list or tuple, the length of it indicates the number of sub-Tensors and the elements in it indicate the sizes of sub-Tensors’ dim dimension orderly. The length of the list mustn’t be larger than the Tensor’s size of dim .

  • dim (int32|Varible, optional) – A scalar with type int32 or a Tensor with shape [1] and type int32. The dimension along which to split. If \(dim < 0\), the dimension to split along is \(rank(input) + dim\). Default is -1.

  • name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name .

Returns

The list of segmented Tensor variables.

Return type

list(Variable)

Raises

  • TypeError – num_or_sections is not int, list or tuple.

  • TypeError – dim is not int or Variable.

Example

import paddle.fluid as fluid

# input is a variable which shape is [3, 9, 5]
input = fluid.data(
     name="input", shape=[3, 9, 5], dtype="float32")

x0, x1, x2 = fluid.layers.split(input, num_or_sections=3, dim=1)
# x0.shape [3, 3, 5]
# x1.shape [3, 3, 5]
# x2.shape [3, 3, 5]

x0, x1, x2 = fluid.layers.split(input, num_or_sections=[2, 3, 4], dim=1)
# x0.shape [3, 2, 5]
# x1.shape [3, 3, 5]
# x2.shape [3, 4, 5]

x0, x1, x2 = fluid.layers.split(input, num_or_sections=[2, 3, -1], dim=1)
# x0.shape [3, 2, 5]
# x1.shape [3, 3, 5]
# x2.shape [3, 4, 5]