- paddle. unstack ( x, axis=0, num=None )
This layer unstacks input Tensor
xinto several Tensors along
axis< 0, it would be replaced with
numis None, it would be inferred from
x.shape[axis], and if
x.shape[axis]<= 0 or is unknown,
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.
list(Tensor), The unstacked Tensors list. The list elements are N-D Tensors of data types float32, float64, int32, int64.
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]