# QA Official

### kears some examples

https://qaofficial.com/post/2019/04/06/69227-kears-some-examples.html 2019-04-06
1, softmax multi-classification based on multilayer perceptron ### 基于多层感知器的softmax分类 from keras.models import Sequential from keras.layers import Dense,Dropout,Activation from keras.optimizers import SGD import keras # Generate dummy data import numpy as np x_train = np.random.random((1000,20)) ### 将类别向量(从0到nb_classes

### reshape Function-Differences between reshape Functions of Matlab and opencv

https://qaofficial.com/post/2019/04/06/69159-reshape-function-differences-between-reshape-functions-of-matlab-and-opencv.html 2019-04-06
opencv: m: 1 2 3 4 m.reshape(0, 1): 1 2 3 4 m.reshape(0, 4): 1 2 3 4 请按任意键继续. . . Matlab: It can be seen that OPENCV is row first and matlab is column first. on this small issue, let me n long training are all misplaced!!!!

### C# Several Common Algorithms

https://qaofficial.com/post/2019/04/05/111713-c#-several-common-algorithms.html 2019-04-05
1. Find the value of the following expression and write down one or more implementations you think of: 1-2+3-4+…+m static int F1(int m) { int sum =0; bool flag =true; for (int i = 1; i <= m; i++) { if (flag) //一次是默认是True，下下也为T

### GitHub Learning Notes (2) Upload to Warehouse

1. Register on GitHub; Second, Baidu Git and download; Three, to operate the file Then right click on the folder interface to be uploaded locally and click git bash here. after clicking, git bash will pop up automatically, and then the folder can be operated by inputting commands into git bash; 4. Building a warehouse on GitHub; Five, to connect: 1. input git init: initialize this folder as a git warehouse;

### R Machine Learning One: kNN Algorithm Case

https://qaofficial.com/post/2019/04/05/68933-r-machine-learning-one-knn-algorithm-case.html 2019-04-05
kNN algorithm Advantages: It is highly unbiased and does not require any assumptions about the data.Simple, effective and easy to implement Disadvantages: Since there is no abstract process involved, kNN has not actually created a model and the prediction time is long. case study: detection of prostate cancer Step 1 : 100 observation 10 variables, including 8 numerical variables, a category variable, an ID: 1，Radi

### ROS Basic Learning Notes (1)

https://qaofficial.com/post/2019/04/05/69059-ros-basic-learning-notes-1.html 2019-04-05

### SVM Learning Summary (1) How to Learn SVM

https://qaofficial.com/post/2019/04/05/68966-svm-learning-summary-1-how-to-learn-svm.html 2019-04-05
1. Preface I have been studying SVM algorithm for a long time. I always thought it was a very simple algorithm, but I didn't think it was very difficult when I was studying it. I am still not familiar with convex optimization. I have to strengthen it in the future. I will mainly talk about the learning ideas of SVM algorithm (for small white beginners). 2. Learning Methods Through the comparative study of various materials, I personally think that using chapter 7 of Li Hang's "

### SVM explanation and code

https://qaofficial.com/post/2019/04/05/68970-svm-explanation-and-code.html 2019-04-05
Support Vector Machine is commonly referred to as SVM because its English name is SupportVectorMachine. Generally speaking, it is a two-class classification model. Its basic model is defined as the linear classifier with the largest interval in the feature space. Its learning strategy is interval maximization, which can be converted into the solution of a convex quadratic programming problem. Two Main Contents: 1. How did the original formula come from

### jQuery determines which li is currently clicked

https://qaofficial.com/post/2019/04/05/111683-jquery-determines-which-li-is-currently-clicked.html 2019-04-05
Use $(this).index () to get the subscript of li. The following is an example of style substitution:$("#aa li").click(function(){ $("#aa li").removeClass("class名字，多个class用空格分开");$(this).a