当前位置:网站首页>20220524 深度学习技术点
20220524 深度学习技术点
2022-06-12 07:35:00 【GAOSHIQI5322688】
1、1*1卷积核作用,降维
1*1卷积核的作用_nefetaria的博客-CSDN博客_1*1卷积核的作用
2、图像语义信息
对图像中语义信息、高层和底层特征的理解_Brucechows的博客-CSDN博客_低层特征和高层特征
FPN解决小物体检测,高语义
3、select search
Selective Search (选择搜索)_JNingWei的博客-CSDN博客_search selective
4、卷积核的优势
卷积核的优势-权值共享与局部感知能力_椰楠liu的博客-CSDN博客_卷积层局部感知
5、神经元、每个神经元连接数
什么是卷积神经网络中的-----“神经元”以及“连接数”_ct雨田的博客-CSDN博客_卷积神经网络神经元
6、ROI pooling. 特征池化
ROI POOLING 介绍 - 善良的大猪猪 - 博客园
7、过拟合原因
网络层很深参数多,数据过少,容易产生
8、归一化区别
输入归一化、批量归一化(BN)与层归一化(LN)_璇焱如柳的博客-CSDN博客_层归一化
9、ocr置信度
视频OCR中的文本置信度阈值(threshold)参数有什么作用?_视频分析服务 VAS_常见问题_华为云
10、深度学习head、neck、backbone三个术语分别是指什么?
深度学习head、neck、backbone三个术语分别是指什么?_AI界扛把子的博客-CSDN博客_深度学习head
11、yolo损失函数
http://www.136.la/jingpin/show-141192.html
12、图像中的掩膜(Mask)是什么_bitcarmanlee的博客-CSDN博客_掩膜
13、人脸识别
一般来说,人脸识别分三步走:
- 找人脸:图片中找出含人脸的区域框出来
- 对齐人脸:将人脸的眼镜鼻子嘴巴等标出来,以此作为依据对齐人脸
- 识别:将对齐的人脸进行识别,判定这张脸究竟是谁
14、度量学习
Metric Learning——度量学习 - 常给自己加个油 - 博客园
15、图像淹模、连通域
图像中的掩膜(Mask)是什么_bitcarmanlee的博客-CSDN博客_掩膜
OpenCV——图像连通域_我有一個夢想的博客-CSDN博客_opencv 连通域
16、sift图像匹配
SIFT图像匹配_Yep_Ying的博客-CSDN博客_sift图像匹配
17、标注原则
边栏推荐
- Personalized federated learning with exact stochastic gradient descent
- [college entrance examination] prospective college students look at it, choose the direction and future, and grasp it by themselves
- There is no solid line connection between many devices in Proteus circuit simulation design diagram. How are they realized?
- ‘CMRESHandler‘ object has no attribute ‘_ timer‘,socket. gaierror: [Errno 8] nodename nor servname pro
- Logistic regression
- Scoring prediction problem
- MySQL index (easy to handle in one article)
- LED lighting experiment with simulation software proteus
- R语言使用epiDisplay包的summ函数计算dataframe中指定变量在不同分组变量下的描述性统计汇总信息并可视化有序点图、使用dot.col参数设置不同分组数据点的颜色
- Generalized semantic recognition based on semantic similarity
猜你喜欢

Leverage contextual information

Chapter V - message authentication and digital signature

Exposure compensation, white increase and black decrease theory

经典论文回顾:Palette-based Photo Recoloring

Explain ADC in stm32

Study on display principle of seven segment digital tube

2022 simulated test platform operation of hoisting machinery command test questions

Demonstrate "topic communication, action communication, service communication and parameter server" with a small turtle case

2022 electrician (elementary) examination question bank and simulation examination

LED lighting experiment with simulation software proteus
随机推荐
R语言将dataframe数据中指定数据列的数据从小数转化为百分比表示、数据转换为百分数
Voice assistant -- Qu -- semantic role annotation and its application
Paddepaddl 28 supports the implementation of GHM loss, a gradient balancing mechanism for arbitrary dimensional data (supports ignore\u index, class\u weight, back propagation training, and multi clas
Bi skills - beginning of the month
Shortcut key modification of TMUX and VIM
Set up a remote Jupiter notebook
Golang quickly generates model and queryset of database tables
Voice assistant - Introduction and interaction process
2022R2移动式压力容器充装试题模拟考试平台操作
2022r2 mobile pressure vessel filling test question simulation test platform operation
Formatting the generalization forgetting trade off in continuous learning
2022 electrician (elementary) examination question bank and simulation examination
Thyristor, it is a very important AC control device
tar之多线程解压缩
右击文件转圈卡住、刷新、白屏、闪退、桌面崩溃的通用解决方法
Arrangement of statistical learning knowledge points gradient descent, least square method, Newton method
Vs2019 MFC IP address control control inherits cipaddressctrl class redrawing
R语言使用caTools包的sample.split函数将机器学习数据集划分为训练集和测试集
Unity uses shaders to highlight the edges of ugu I pictures
Leetcode34. find the first and last positions of elements in a sorted array