QA Official

[paper reading notes] batch normalization _ accelerating deep network training by reducing internal co variant shift

https://qaofficial.com/post/2019/04/26/70750-paper-reading-notes-batch-normalization-_-accelerating-deep-network-training-by-reducing-internal-co-variant-shift.html 2019-04-26
prerequisite knowledge:covariate shift, covariate change, i.e. the change of input variable x itself [the input distribution for a learnable system is changing.Generally speaking, the input of each layer of subnetwork is constantly changing during the training process of a network]Batch-Normalization enables the distribution of network layer inputs to present a standard normal distribution [mean value is 0, variance is 1], which can speed up the training of the network [the distribution of each layer of network is different, the required learning rate lr is different, the network system needs to use the lowest lr to ensure the convergence of the model], and can also partially solve the problem of gradient explosion [by reducing the dependence of gradient on the initial value of parameters].

conditional random fields and Code Implementation

https://qaofficial.com/post/2019/04/26/70714-conditional-random-fields-and-code-implementation.html 2019-04-26
条件随机场模型是由Lafferty在2001年提出的一种典型的判别式模型。它在观测序列的基础上对目标序列进行建模,重点解决序列化标注的问题条

convert CompCars dataset to. tfrecord format

https://qaofficial.com/post/2019/04/26/70842-convert-compcars-dataset-to.-tfrecord-format.html 2019-04-26
Preface: Either object detection or object classification needs to process the original image to generate data suitable for training.Object classification-requires an image and its corresponding label.Object detection-requires an image and its corresponding label and (xmin,ymin)(xmax,ymax)Therefore, the data level usually consists of two partsAnnotation-information of stored images, i.e. file name and label sum (xmin,ymin)(xmax,ymax) corresponding to the file name, are usually in the form of xmlImage-image file Common Data Sets: the

front-end face questions summary pen questions

https://qaofficial.com/post/2019/04/26/112109-front-end-face-questions-summary-pen-questions.html 2019-04-26
Front-end Interview Topic 1.the difference between div and span? div is a block-level label and span is a row-level label 2. What are the values of position in html? The default value is What? values: static, relative, fixed, absolute Default: static 3. Which three layers are the front page composed of, respectively, What?The role is What? Front-end Page Composition: Structure Layer, Presentation Layer and Behavior Layer structural layer Created by

how to read papers-summary of "how to read apaper"

https://qaofficial.com/post/2019/04/26/70693-how-to-read-papers-summary-of-ampquothow-to-read-apaperampquot.html 2019-04-26
Abstract Researchers need to spend a lot of time reading papers, not only teachers and researchers, but for some students, especially newly enrolled graduate students, it takes a lot of time to read papers, and often no benefits are seen. This article proposes a three-pass method to help us read an article. It also introduces how to do a literature survey. THE THREE-PASS APPROACH First of all, we are not going to read the paper from beginning to end in detail.

neural network improves mnist recognition rate

https://qaofficial.com/post/2019/04/26/70848-neural-network-improves-mnist-recognition-rate.html 2019-04-26
Follow tensorflow's introductory study to build a neural network to improve the mnist recognition rate, and finally to the correct rate close to 1. Refer to The site code for basic reference, type up and understand the process by yourself, and mark the place in Chinese if you don't know it. # -*- coding:gbk -*- import input_data import tensorflow as tf mnist=input_data.read_data_sets("MNIST_data/", one_hot=True) #添加x作为占

summary of machine learning -GBDT, XGBOOST parameters

https://qaofficial.com/post/2019/04/26/70883-summary-of-machine-learning-gbdt-xgboost-parameters.html 2019-04-26
Experimental Data Set Selection 1. Classification Data Select load_iris The Irises Data Set: from sklearn.datasets import load_iris data = load_iris() data.data[[10, 25, 50]] data.target[[10, 25, 50]] list(data.target_names) list(data.feature_names)2.回归数据选取 from sklearn.datasets import load_boston boston = load_boston() print(boston.data.shape) boston.feature_names 将数

BN and dropout: Some Problems and Considerations

https://qaofficial.com/post/2019/04/25/68654-bn-and-dropout-some-problems-and-considerations.html 2019-04-25
1, BN scale Initialization scale is generally initialized to 1.0. It is associated with sqrt(2.0/Nin), where Nin is the number of input nodes, if random positive distribution is used to initialize weights when using relu activation function.That is, it is larger than the normal method by the square root of 2 (because half of the data after relu becomes 0, so it should be multiplied by the root 2).

FCN Image Semantic Segmentation

https://qaofficial.com/post/2019/04/25/68664-fcn-image-semantic-segmentation.html 2019-04-25
Welcome to course center of Artificial Intelligence Research Network studyai.com ----------------------------------------------------------------------------------- FCN Image Semantic Segmentation-Testing and Training

HTML+JavaScript Displays Current Time

https://qaofficial.com/post/2019/04/25/68805-html-javascript-displays-current-time.html 2019-04-25
HTML: <div id="timeShow"></div> JavaScript: var t=null; t=setTimeout(time,1000); //设置定时器,一秒刷新一次 function time(){ clearTimeout(t); //清楚定时器 dt=new Date(); var y=dt.getYear()+1900; var m=dt.getMonth()+1; var d=dt.getDate(); var weekday=["星期日","