sequence_slice¶

paddle.static.nn. sequence_slice ( input, offset, length, name=None ) [源代码] ¶

实现Sequence Slice(序列切片)运算

该层从给定序列中截取子序列。截取依据为所给的开始 offset （偏移量） 和子序列长 length 。

该API输入只能是LoDTensor, 如果您需要处理的是Tensor类型，请使用 paddle.slice 。

::

输入变量：

1. input (LoDTensor):

   input.data = [[a1, a2], [b1, b2], [c1, c2], [d1, d2], [e1, e2]], input.lod = [[3, 2]], input.dims = (5, 2),

2. offset (Variable):

   offset.data = [[0], [1]]

3. length (Variable):

   length.data = [[2], [1]]

4. name (str|None)

输出变量为LoDTensor：

out.data = [[a1, a2], [b1, b2], [e1, e2]], out.lod = [[2, 1]], out.dims = (3, 2).

import paddle
paddle.enable_static()

import numpy as np
seqs = paddle.static.data(name='x', shape=[10, 5],
                 dtype='float32', lod_level=1)
offset = paddle.assign(np.array([[0, 1]]).astype("int32"))
length = paddle.assign(np.array([[2, 1]]).astype("int32"))
subseqs = paddle.static.nn.sequence_slice(input=seqs, offset=offset,
                                      length=length)