Tag:classifier

  • Parsing JS regular expression

    Time:2021-7-22

    JS regular expression Regular expression is a logical formula for string operation Here we recommend an online testing website for regular expressionsRegular expression online testing regular grammars In JavaScript, a regular expression is also an object, an index type. *Using a regular expression literal quantity is the easiest way. Two / are regular expression delimiters. […]

  • Opencv Python vehicle identification project

    Time:2021-7-14

    Image vehicle identification According to the article set up a good environment to start the projectlink import sys import cv2 from PyQt5.QtGui import * from PyQt5.QtWidgets import * from PyQt5.QtGui import QIcon, QPalette, QPixmap, QBrush, QRegExpValidator class mainWin(QWidget): def __init__(self): “”” Constructors “”” super().__init__() self.initUI() Self. Openbtn. Clicked. Connect (self. OpenFile) # signal and slot […]

  • Neural networks are cute

    Time:2021-5-29

    Neural network is very cute! 0. ClassificationThe most important use of neural network is classification. In order to give you an intuitive understanding of classification, let’s take a look at a few examplesSpam identification: now there is an e-mail that extracts all the words that appear in it and sends them to a machine. The […]

  • Using pytorch to train an image classifier instance

    Time:2021-5-9

    As follows: import torch import torchvision import torchvision.transforms as transforms import matplotlib.pyplot as plt import numpy as np print(“torch: %s” % torch.__version__) print(“tortorchvisionch: %s” % torchvision.__version__) print(“numpy: %s” % np.__version__) Out: torch: 1.0.0 tortorchvisionch: 0.2.1 numpy: 1.15.4 Where does the data come from? Generally speaking, you can load image, text, audio and video data into […]

  • Basic summary regular expressions

    Time:2021-5-8

    1、 Reference Introduction to regular expressions 2、 Foundation 2.1 quantifier metacharacter expression explain Examples * >= 0 + >1 ? <=1 {m} =m {m,} >=m {m,n} >=m <=n

  • [paper anatomy] cvpr2020 SDRC

    Time:2021-5-4

    [paper anatomy] cvpr2020 unsupervised domain adaptation via structurally regulated deep clustering This article is the article of 2020cvpr, the article uses the clustering method to adapt to the domain, and the effect is outstanding in 20 years on the commonly used data sets. Recent work is similar to this idea. Let’s investigate. abstract Transfer learning […]

  • Cpndet: crudely add two stage fine tuning to centernet, faster and stronger | ECCV 2020

    Time:2021-4-20

    This paper is published by the authors of centernet, and proposes an anchor free / two-stage target detection algorithm CPN, which uses key points to extract candidate box, and then uses two-stage classifier to predict. The overall idea of this paper is very simple, but the accuracy and reasoning speed of CPN are very good, […]

  • Opencv Development Notes (55): red fat 8 minutes to take you in-depth understanding of Haar, LBP features and cascade classifier recognition process

    Time:2021-4-19

    If the article is original, it can’t be reproduced without permissionOriginal blog address: https://blog.csdn.net/qq21497936Original blog navigation: https://blog.csdn.net/qq21497936/article/details/102478062Blog address: https://blog.csdn.net/qq21497936/article/details/106144767Dear readers, knowledge is boundless and manpower is poor. Either change the demand, or find professionals, or do research on your ownRed fat man (red imitation) blog: development technology collection (including QT practical technology, raspberry pie, 3D, […]

  • ES6 (8) – regexp

    Time:2021-4-18

    RegExp Sticky — y modifier On regularization of Chinese — u modifier Multibyte Chinese character matching Dot character Add a new Unicode code point to match Chinese characters classifier I modifier Predefined patterns Es6-es10 learning map Sticky — y modifier Y means sticky, global matching, must start from the first, continuous matching const s = […]

  • [technology blog] confrontational domain adaptation

    Time:2021-4-10

    Introduction to domain adaptation Domain adaptation is one of the most common problems in transfer learning. The domains are different but the tasks are the same, and the source domain data has labels, the target domain data has no labels or very few data has labels.Domain adaptation projects the features of the source domain and […]

  • What is a neural network?

    Time:2021-4-7

    I know a radius r as a parameter, and I want to make a nice face. There are 10 pictures in my brain capacity, which are: obscene man, big beauty, tech house, little Lori, little Zhengtai, grandma, dinosaur sister, Gao fushai, Laozi, Phoenix man. At this time, the user said, these are not good-looking, I’ll […]

  • Python implementation of AdaBoost algorithm based on single decision tree

    Time:2021-3-24

    import numpy as np import matplotlib.pyplot as pltdef loadDataSet(fileName): “”” Read data set : param file name: file name : Return: returns the dataset and data label in the form of a list “”” #Get the number of features numFeat = len(open(fileName).readline().split(‘\t’)) #Define an empty list to save features dataMat = [] #Define an empty […]