当前位置:网站首页>【CNN记录】tensorflow slice和strided_slice
【CNN记录】tensorflow slice和strided_slice
2022-08-02 02:23:00 【侵蚀昨天】
两个函数都是从张量中提取切片
slice
tf.slice(input,begin,size,name=None)
参数说明:
input:输入数据
begin:是一个list,切片索引,对应各个维度,例如[0,1,2],三个维度分别冲0、1、2开始
size:是一个list,对应begin中指定位置开始,取多少元素举个栗子
import tensorflow as tf
import numpy as np
#一个4x2x3的tensor
input = tf.constant([[[1, 1, 1], [2, 2, 2]],
[[3, 3, 3], [4, 4, 4]],
[[5, 5, 5], [6, 6, 6]],
[[7, 7, 7], [8, 8, 8]],
])
out=tf.slice(input, [2, 0, 0], [2, 1, 2])
print(out)
输出:
tf.Tensor(
[[[5 5]]
[[7 7]]], shape=(2, 1, 2), dtype=int32)第一个维度从2开始取2个,即变为
[[[5, 5, 5], [6, 6, 6]],
[[7, 7, 7], [8, 8, 8]]]
第二个维度从 0开始取1个,即变为
[[[5, 5, 5]],
[[7, 7, 7]]]
第三个维度从0开始取2个,即变为
[[[5, 5]],
[[7, 7]]]
strided_slice
tf.strided_slice(
input_, begin, end, strides=None, begin_mask=0, end_mask=0, ellipsis_mask=0,
new_axis_mask=0, shrink_axis_mask=0, var=None, name=None)
参数解释:
input_:输入数据
begin:是一个list,切片索引,对应各个维度
end:是一个list,终止切片索引(开区间),对应各个维度终止索引
strides:各个维度进行切片的步长,不设置即为1
举个栗子,和前面一样
import tensorflow as tf
import numpy as np
#一个4x2x3的tensor
input = tf.constant([[[1, 1, 1], [2, 2, 2]],
[[3, 3, 3], [4, 4, 4]],
[[5, 5, 5], [6, 6, 6]],
[[7, 7, 7], [8, 8, 8]],
])
out = tf.strided_slice(input, [1, 0, 0], [4, 1, 2],[2,1,1])
print(out)
输出:
tf.Tensor(
[[[3 3]]
[[7 7]]], shape=(2, 1, 2), dtype=int32)
第一个维度从1开始 区间[1,4),步长为2,切片为
[[[3, 3, 3], [4, 4, 4]],
[[7, 7, 7], [8, 8, 8]]]
第二个维度从0开始 区间[0,1),步长为1,切片为
[[[3, 3, 3]],
[[7, 7, 7]]]
第二个维度从0开始 区间[0,2),步长为1,切片为
[[[3, 3],],
[[7, 7]]]
边栏推荐
- MySQL - CRUD operations
- ros多客户端请求服务
- AntPathMatcher uses
- PHP uses PHPRedis and Predis
- The failure to create a role in Dahua Westward Journey has been solved
- 微信小程序异步回调函数恶梦和解决办法
- 2022河南青训联赛第(三)场
- From 2023 onwards, these regions will be able to obtain a certificate with a score lower than 45 in the soft examination.
- MySQL8 download, start, configure, verify
- 【ORB_SLAM2】void Frame::AssignFeaturesToGrid()
猜你喜欢

字符串常用方法

Analysis of the status quo of digital transformation of manufacturing enterprises
![[LeetCode Daily Question] - 103. Zigzag Level Order Traversal of Binary Tree](/img/b9/35813ae2972375fa728e3c11fab5d3.png)
[LeetCode Daily Question] - 103. Zigzag Level Order Traversal of Binary Tree

四元数、罗德里格斯公式、欧拉角、旋转矩阵推导和资料

oracle query scan full table and walk index

十字光标太小怎么调节、CAD梦想画图算量技巧

2022-08-01 mysql/stoonedb慢SQL-Q18分析

A good book for newcomers to the workplace

Power button 1374. Generate each character string is an odd number

Project Background Technology Express
随机推荐
记一个gorm初始化的坑
Golang分布式应用之定时任务
Garbage Collector CMS and G1
Nanoprobes多组氨酸 (His-) 标签标记:重组蛋白检测方案
2022 Henan Youth Training League Game (3)
29. 删除链表中重复的节点
极大似然估计
面对职场“毕业”,PM&PMO应该如何从容的应对?如何跳槽能够大幅度升职加薪?
用位运算为你的程序加速
数值积分方法:欧拉积分、中点积分和龙格-库塔法积分
AI目标分割能力,无需绿幕即可实现快速视频抠图
TKU remembers a single-point QPS optimization (I wish ITEYE is finally back)
Nanoprobes Polyhistidine (His-) Tag: Recombinant Protein Detection Protocol
What to study after the PMP exam?The soft exam ahead is waiting for you~
Software testing Interface automation testing Pytest framework encapsulates requests library Encapsulates unified request and multiple base path processing Interface association encapsulation Test cas
2022-08-01 安装mysql监控工具phhMyAdmin
Centos7 安装postgresql并开启远程访问
JVM调优实战
软件测试 接口自动化测试 pytest框架封装 requests库 封装统一请求和多个基础路径处理 接口关联封装 测试用例写在yaml文件中 数据热加载(动态参数) 断言
A good book for newcomers to the workplace