QA Official

Python Implementation of dropout Layer (Including dropout Function and Forward Reverse propagator with Dropout)

https://qaofficial.com/post/2019/04/08/69449-python-implementation-of-dropout-layer-including-dropout-function-and-forward-reverse-propagator-with-dropout.html 2019-04-08
Reference: https://zhuanlan.zhihu.com/p/29592806 # -*- coding:utf-8 -*- import numpy as np def dropout(X, keep_prob = 0.5): """ :param X: input :param keep_prob: :return: """ D = np.random.rand(X.shape[0], X.shape[1]) # step1: initialize matrix d D = D < keep_prob # step2: convert entries of d X = X * D # step3: shut down some neuron X = X/keep_prob #step4: scale the value of neuron return X ''' numpy.random.rand(do,d1, ...,dn) create an

Read and Write of imagenet markup files

https://qaofficial.com/post/2019/04/08/69484-read-and-write-of-imagenet-markup-files.html 2019-04-08
image_label_util.py #coding:utf-8 import os, cv2, shutil, random, codecs, HTMLParser from lxml import etree from lxml.etree import Element, SubElement, tostring class PicAnno: objects = [] def __init__(self, folder): self.objects = [] self.folder = folder def set_folder(self, folder): self.folder = folder def set_filename(self, filename): self.filename = filename def set_size(self, width, height, depth): self.width = width self.height = height self.depth = depth def add_object(self, object): self.objects.append(object) class PicObject: def __init__(self, name): self.name =

Timer and Multithreading

https://qaofficial.com/post/2019/04/08/69493-timer-and-multithreading.html 2019-04-08
Recently, when I was working on a project, I encountered a video capture image.The use of timers is somewhat intertwined with the use of multithreading.The timer was originally used to test, because the project needs to occupy more Central Processor, so obviously the image display comparison card. So I checked it online.Post it to everyone to learn. software timer and multithreading are widely used in control engineering, mainly because during the control process, there will be a large amount of Socket communication and serial communication data.

[Deep Learning: CNN】Dropout Analysis (1)

https://qaofficial.com/post/2019/04/08/69445-deep-learning-cnndropout-analysis-1.html 2019-04-08
1: Introduction Because in some models of machine learning, if the parameters of the model are too many and the training samples are too few, then the trained model is prone to over-fitting.One of the problems often encountered in training bp network is over-fitting, which means that the loss function of the model on training data is relatively small and the prediction accuracy is relatively high (if represented by drawing,

[Recursive Method] Step Jump/Advanced Step Jump/Abnormal Step Jump

https://qaofficial.com/post/2019/04/08/69526-recursive-method-step-jump/advanced-step-jump/abnormal-step-jump.html 2019-04-08
Step Jump 1. Topic a frog (clam?) You can jump up one step at a time, or you can jump up two steps.Find out how many jumping methods the frog can use to jump up an n-step. 2. Ideas 只有两种可能,即跳1级或2级。 | 阶梯级数 | 跳台阶的可能性 | 跳法

arbitrage model

https://qaofficial.com/post/2019/04/08/69567-arbitrage-model.html 2019-04-08
3 to buy, 5 to sell The so-called carry trade is to buy high-interest currencies and sell low-interest currencies to earn interest spread. Now high-interest currencies include New York, RMB and Australian dollars.Of course, there are currencies of emerging market countries, such as Turkey and Vienna.The option of carry trade is to choose a currency that will stabilize promotion, or what if depreciation exceeds interest income?For example, the RMB in previous years, from 6.

brick removal problem

https://qaofficial.com/post/2019/04/08/69585-brick-removal-problem.html 2019-04-08
Problem Description Xiao Ming is now loved by everyone. Gao Fushuai, with flowers blooming in Hanami, is immersed in beautiful women's music and dancing all day long.However, people don't know anything about it. Xiao Ming, who was very proud of himself, had a hard struggle. Xiao Ming didn't cut off his long hair at that time, didn't have a credit card, didn't have her, didn't have a 24-hour hot water

calculate Fisher vector and VLAD

https://qaofficial.com/post/2019/04/08/69623-calculate-fisher-vector-and-vlad.html 2019-04-08
This short tutorial shows how to compute Fisher vector and VLAD encodingswith VLFeat MATLAB interface. These encoding serve a similar purposes: summarizing in a vectorial statistic a number of local feature descriptors (e.g. SIFT).Similarly to bag of visual words, they assign local descriptor to elements in a visual dictionary, obtained with vector quantization (KMeans) in the case of VLAD or a GaussianMixture Models for Fisher Vectors. However, rather than storing visual word occurrences only, these representations store a statistics of the difference between dictionary elements and pooled local features.

from civil engineering to it-a little experience of brick-moving men (1)

https://qaofficial.com/post/2019/04/08/69578-from-civil-engineering-to-it-a-little-experience-of-brick-moving-men-1.html 2019-04-08
The air in the school is still full of the smell of leaves. The downstairs of the dormitory is full of all kinds of people, some seeing off and some crying. In short, five years of college career is officially over (why do you say five years is also caused by yourself?..)。Before I knew what was going on, I set foot on the train to Beijing. In the next half month, inside will go to the X Group University Graduate Training Base in Beijing for half a month's training.

into the pit Guide to Machine Learning (IV): Multiple Linear Regression

https://qaofficial.com/post/2019/04/08/69630-into-the-pit-guide-to-machine-learning-iv-multiple-linear-regression.html 2019-04-08
After learning "Simple Linear Regression", we further learn to apply more extensive multivariate linear regression and implement it using Python code. 1. Understanding Principle multiple linear regression is a generalization of simple linear regression and has different characteristics from simple linear regression. 1 concept * * Multiple Linear Regression)** Try to find a linear equation through known data to describe the relationship between two or more features (independent variables) and