QA Official

heteroscedasticity 2019-04-27
Is the following statement about Heteroskedasticity correct? A. Linear regression has different error terms B linear regression has the same error term C. Linear regression error term is zero D none of the above statements is true. answer: a Analysis: heteroscedasticity is relative to the same square difference. The so-called homodyne is to ensure that the regression parameter estimators have good statistical properties. An important assumption of the classical linear regression model is that the random errorterm in the overall regression function satisfies homoscedasticity, that is, they all have the same variance.

tendorflow slim resnetv2 source code reading notes 2019-04-27
mainly involves: First, it is recommended to read the official documents of Tensorflow and slim to acquire basic knowledge of arg_scope, variable_scope, outputs_collections, etc. This article mainly records the general logic and memo of the code. ''' 需了解collections.namedtuple,相当于一个命

what is the relationship between spring container and spring mvc container? 2019-04-27
From: parent-child container relationship between spring and SpringMVC

CPM Paper Translation (CVPR2016) 2019-04-26
ABSTRACT attitude machine provides a continuous frame estimation for learning rich hidden space models.We systematically design a convolution network for pose recognition, which can learn image features and image-dependent spatial models.Contribution of the paper: Implicit modeling of long-distance relationships (joints).We design a cascade network structure, which consists of a convolution network with the trust graph of the previous network input.It improves the estimation of components layer by layer without using explicit graph models as references.

CVPR2018 paper list 2019-04-26
CVPR2018 paper list Abstract object tracking is the cornerstone of many visual analysis systems.In recent years, although considerable progress has been made in this area, it is still a challenge to track in real video steadily, efficiently and accurately.In this paper, we propose a hybrid tracker, which uses motion information from compressed video streams and a general semantic object detector acting on decoded frames to build a fast and effective tracking engine.

GBDT&GBRT 2019-04-26
GBDT (Gradient Boosting Decision Tree): Gradient Lifting Decision Tree GBRT (Gradient Boosting Regression Tree): Gradient Ascension Regression Tree CART(Classification And Regression Tree) In Boosting algorithm, when the square error loss function is adopted, the loss function just expresses the fitting residual of the current model, which is convenient for optimization.It is also very convenient when using exponential loss function.But for General function, optimization is very difficult.Therefore, the steepest descent approximation method, that is, the negative gradient of the loss function in the current model, is used as the approximation of the residual error of Boosting algorithm in the regression problem.

Java Data Structure: Sort Algorithm (Bubble Sort, Select Sort, Insert Sort, Shell's Sort, Quick Sort, heapsort and Merge sort) 2019-04-26
public class 冒泡排序 { public static void main(String[] args) { int a[] = { 1, 9, 6, 8, 5, 65, 65, 84, 1, 2, 5, 23, 7, 889 }; for (int i = 0; i < a.length - 1; i++) { //使用两个for循环遍历 for (int j = 0; j < a.length - i - 1; j++)

RF, GBDT, XGBoost interview level finishing 2019-04-26
Since this article is based on interview, it will not pay too much attention to formulas and derivation. If you want to know the algorithm in detail, please look forward to the following.RF, GBDT and XGBoost all belong to Ensemble Learning. The purpose of Ensemble Learning is to improve the generalization ability and robustness of a single learner by combining the prediction results of multiple base learners.According to the generation method of individual learners, the current integrated learning methods can be roughly divided into two categories: strong dependency between individual learners, serialization method that must be generated serially, and parallelization method that can be generated simultaneously without strong dependency between individual learners.

URL encoding processing 2019-04-26
1. In mobile development, we will encounter situations where a web address can be loaded on a browser, but cannot be loaded on an App, or the web address cannot be parsed, etc.This kind of situation is mostly caused by the fact that the website contains very vulgar characters, including Chinese characters.There are many ways to deal with this kind of reason, and the Internet is full of them.However, with

VGG, ResNet, GoogleLeNet, AlexNet and other common network codes and pre-training models 2019-04-26
Common Data Sets: ImageNet Microsoft's Coco CIFAR-10 and Cifar-100 PASCAL VOC  Overview of top-5 Error Rate of Models in ImageNet Competition: Common Pre-training Model Pool: AlexNet:AlexNet Code and Models (CAFFE (Convolutional Architecture for Fast Feature Embedding)) HTTPS:// (Convolutional Architecture for Fast Feature Embedding)/Tree/Master/Models/BVLC _ AlexnetFine tune AlexNet to fit any data set (Tensor Flow) _ Alexnet _ with _ Tensor Flow