unstack

paddle. unstack ( x, axis=0, num=None ) [source]
Alias_main

paddle.unstack :alias: paddle.unstack,paddle.tensor.unstack,paddle.tensor.manipulation.unstack :old_api: paddle.fluid.layers.unstack

UnStack Layer

This layer unstacks input Tensor x into several Tensors along axis.

If axis < 0, it would be replaced with axis+rank(x). If num is None, it would be inferred from x.shape[axis], and if x.shape[axis] <= 0 or is unknown, ValueError is raised.

Parameters

  • x (Tensor) – Input Tensor. It is a N-D Tensors of data types float32, float64, int32, int64.

  • axis (int) – The axis along which the input is unstacked.

  • num (int|None) – The number of output variables.

Returns

The unstacked Tensors list. The list elements are N-D Tensors of data types float32, float64, int32, int64.

Return type

list(Tensor)

Raises

ValueError – If x.shape[axis] <= 0 or axis is not in range [-D, D).

Examples

import paddle
x = paddle.ones(name='x', shape=[2, 3, 5], dtype='float32')  # create a tensor with shape=[2, 3, 5]
y = paddle.unstack(x, axis=1)  # unstack with second axis, which results 3 tensors with shape=[2, 5]