自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(38)
  • 资源 (1)
  • 收藏
  • 关注

原创 How to type approximate symbol(≈) quickly

Just hold your "Alt" then press 2,4,7

2024-02-17 14:39:19 404

原创 查看ubuntu版本号

cat /etc/issue

2024-01-16 11:30:05 371

原创 vs code-debug can‘t find file

【代码】vs code-debug can‘t find file。

2024-01-09 19:39:48 424

原创 github GnuTLS recv error (-110): The TLS connection was non-properly terminated.

【代码】github GnuTLS recv error (-110): The TLS connection was non-properly terminated.

2023-12-02 22:04:59 427

原创 github timeout when using the VPN

【代码】github timeout when using the VPN。

2023-12-02 21:57:36 568

转载 Optical Flow

Brief introduction and practice for the Optical flow in opencv

2022-08-31 12:45:33 106 1

原创 手把手教你Linux下基于ITK开发基础(1)

linux下医学图像处理库ITK

2022-08-26 11:57:28 1072

翻译 对比学习学习笔记

翻译文章,少少部分自己理解添加

2022-01-13 20:09:05 564

原创 迁移学习:模型的保存和载入(pytorch版)

有待完善

2022-01-12 17:00:25 800

原创 迁移学习:自己预训练的resnet18模型在Unet上的实现(pytorch版)(有待完善)

文末有resnet18网络结构下面上一张unet的网络结构然后根据以上的网络结构图,搭建pytorch模型def Conv2RELU(inchannels, outchannels, kernel, padding): return nn.Sequential( nn.Conv2d(inchannels, outchannels, kernel, padding=padding), nn.ReLU(inplace=True), )cla.

2022-01-07 16:40:52 3826 3

原创 Learning diary

Unpack the tuplesplit the string through "str"str.split(str="", num=string.count(str))split by filename and path

2020-03-24 00:37:24 266

原创 Python: variadic parameters(*) and keyword parameters(**)

There is a question:I want to define a function to add all elements in a list that I created just now,how can I do that?Here is the common answer:def add(my_list): sum = 0 for list i...

2020-03-23 23:49:18 143

原创 How to load and save nii and dicom file

load and save medical images

2020-01-08 15:41:45 197

原创 opencv & plt可视化显示nii中的slice

Extractingdata:1.nibableimport nibabel as nibnii_1 = nib.load(img1_path)nii_1 = nii_1.dataobj #obtain the nii datanii_2 = nib.load(img2_path)nii_2 = nii_2.dataobj #obtain the nii data2.Sim...

2020-01-03 12:57:34 1015

翻译 Effective tensorflow 2(why tensorflow 2.0)

Translation of the article in this link:https://www.tensorflow.org/guide/effective_tf2高效的tensorflow 2为了让用户在使用tensorflow的时候更加高效,在tensorflow 2.0 中有许多的改进。tensorflow去除了多余的API,让tensorflow中的API更有一致性(统一了...

2019-10-26 17:05:11 140

原创 Note for tensorflow API

tf.splittf.split( value, num_or_size_splits, axis=0, num=None, name='split')If num_or_size_splits is an integer, then value is split along dimension axis into num_split smal...

2019-08-27 16:25:05 84

原创 Loss Function

Dice lossDefinition of dice coefficient The original formular is apply for discrete data,Given two set X and Y. the dice loss is: ...

2019-07-07 17:07:09 660

转载 How to solve “MobaXterm X11: Proxy authorization not recognized” Error

http://www.onwardpath.com/2018/07/09/1368.htmlThe link above indeed solved my problem

2019-07-05 19:45:09 1871

原创 some bugs when using server(To be continue)

1.when you want to autocomple the commod by using table,you see the following graphIn addition,I can't use the pycharm,either.I check out the usage of all the partitions,the / partition is ful...

2019-05-12 16:48:20 123

原创 Config my new linux server(to be continue)

add user:add -d /home/myname-m myname (create an user while create a home folder for user)python:change your default version of python.the default python is python2,but we constantly need py...

2019-03-14 20:09:21 86

原创 some tricks for linux

shell:(1)Couse I spend too much time on the windows,I used to open a folder and see the filessimultaneously.so I serched some blogs to achive this fuction in linux,here is the method.vim ~/.bash...

2019-03-14 19:01:30 99

原创 Some collections for learning

Two webs for downloading ebooks and papers:https://b-ok.cc/s/?q=&yearFrom=&yearTo=&language=&extension=&t=0http://gen.lib.rus.ec/Some webs for reading paper:https://www...

2019-03-06 22:13:29 157

翻译 Install OpenCV-Python in Ubuntu(translation)

Here is the translation for document inhttps://docs.opencv.org/master/d2/de6/tutorial_py_setup_in_ubuntu.htmlIf there are some issues,pleasepoint it out,I'll appreciate that you can tell my mistak...

2019-03-06 14:42:04 138

原创 image segmentation(to be continue)

canny:canny's approach is based on three basic objectives:1.low error rate.All eadge should be found,and there should be no spurious responses.2.Edge points should be well localized.3.Single e...

2019-03-05 22:09:43 155

转载 HOG/Haar/LBP(incomplete)

reprinted from:https://www.cnblogs.com/zhehan54/p/6723956.html(一)HOG特征1、HOG特征:方向梯度直方图(Histogram of Oriented Gradient, HOG)特征是一种在计算机视觉和图像处理中用来进行物体检测的特征描述子。它通过计算和统计图像局部区域的梯度方向直方图来构成特征。Hog特征结合SVM分类...

2019-03-05 20:13:21 147

原创 record for the keyboard shortcut of vim(to be continue)

ctrl+x then ctrl+f:complete the filenamectrl+p:complete the previously created word:e+filename/folder:open a new file or a folder:sv+filename:open a new file in the same screen(vs)...

2019-03-05 11:29:59 85

原创 the moment of picture

Definition: a moment set calculating from a picture usually describe the whole feature of the image,and indicate the substantial imformation of different geometrical features,like size,shape,position ...

2019-02-22 21:34:59 154

原创 Paper note(1):New machine-learning technologies for computer-aided diagnosis

there is the paper:The methods of AI remain relatively uncommon in clinical practice for at least two reasons.First,machine-learing algorithms may not perform well when applied to new dataSeco...

2018-12-30 16:09:56 145

原创 Add a new kernel of jupyter notebook for windows

when you use the anaconda,It’s significant that you should know the conception of environment.In my standpoint,It’s a very good library manager just like the docker.Once you installed the anaconda,you...

2018-12-23 19:57:50 185

原创 python machine learning(Apply for KNN Algorithm)

Following is a simple instance of KNN algorithmOur goal is to build a machine learning model that can learn from the measurement of these irises whose species is known,so that we can predict the spec...

2018-11-18 17:39:06 115

原创 Note for foundation of mathematical in image processing

                    

2018-11-04 20:00:24 100

原创 解决Ubuntu下的WiFi列表不显示问题(硬件禁止问题)

查阅了很多博客,其实可能问题会有相似的,但产生的原因可能各不相同,我的环境是win7+Ubuntu16.04的双系统,装好系统后各项功能是完好的,但是第二天开机的时候就出现了连不上网的问题,尝试了很多方法,开始以为是无线驱动的问题,但又查了一些人的博客通过rfkill list命令查看驱动发现网卡是在的,只不过我发现了问题就是我的一个驱动的hard blocked是yes(...

2018-10-19 14:03:50 21145 2

原创 Image processing by using python,I am the novice

I am learning the Image processing,so I have to learn a programming language to implement  various algorithm,and I just want to learn python,so I choose the python.2018/9/25:At first,I want to do ...

2018-09-25 13:01:29 299

原创 字符指针变量和字符数组的比较

字符数组可以在定义的时候整体的时候赋初值,而不能在赋值语句中整体赋值下面是正确的char str[14]={"i love cs"};下面是错误的char str[14];str[]="i love cs";

2018-03-26 21:00:39 504

原创 stm32文件系统fatfs(零碎笔记)-1

使用spi flash直接存储数据有以下缺点:        1.难以记录有效数据的位置        2.难以确定储存介质的剩余空间        3.不能明确以何种形式解析储存数据文件系统,就是对数据进行管理的方式,使文件系统更加有效的管理储存介质,文件系统可分为ntfs,fat32,exfat等,各种类型的文件管理系统在于管理的模式不同使用文件系统时,他为了储存和管理数据,在储存介质建立了一...

2018-02-27 17:51:22 1260

转载 linux链接库

linux中的动态链接库,和静态链接库是干什么的?转知乎https://www.zhihu.com/question/20484931?sort=created

2018-01-26 00:44:31 241

原创 linux c下求已知三条边的三角形的面积

首先使用的算法有两种:1.用余弦定理求出一个角的余弦,然后求出正弦角A,然后用s=1/2*(a*b*sinA)来求面积;2.直接用海伦公式,p=(a+b+c)/2,s=sqrt(p*(p-a)*(p-b)*(p-c));然后写完的代码如下:#include#includevoid main(){ float p=0,a=0,b=0,c=0,ss=0,s=0;

2018-01-25 23:16:31 861

原创 esp8266在centos上编译器的安装

配置好环境后,检测一下环境是否有用,可是一直报出下面的错误找了一圈才突然记得之前有看到xtensa-lx106-elf只能在32位系统里才能安装,而我装的是64位的centos7.4,于是百度一下解决办法,只要安装glibc.i686就可以支持了 (yum install glibc.i686)

2018-01-14 21:14:19 458

medsam model

medsam model

2024-02-21

an introduction to probability theory

概率论导论,全英文可以学习学习,作者是费乐,有从基础到深入概率论

2019-01-10

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除