• Face mask detector based on retinanet


    Author | guessCompile VKSource: analytics vidhya introduce Object detection is a very important field in computer vision, which is necessary for automatic driving, video surveillance, medical applications and many other fields. We are fighting an epidemic of unprecedented scale. Researchers around the world are trying to develop a vaccine or a treatment for cowid-19, while […]

  • PSI formula model / data stability index


    Since the model is developed based on the samples of a specific period, whether the model is suitable for the ethnic groups outside the development samples must be tested for stability. The population stability index (PSI) can measure the distribution differences of the scores of test samples and model development samples, and is the most […]

  • OCR Performance Optimization: from neural network to plasticine


    Abstract:In this era of computing power, on the one hand, our researchers are committed to constantly studying the common networks in different scenes, on the other hand, they are committed to optimizing the learning methods of neural networks, which are trying to reduce the computing power resources needed by AI. This article is shared from […]

  • Extreme value theory of R language: analysis of fire loss distribution based on GPD model


    Link to the original text:http://tecdat.cn/?p=21425  Extreme value theory focuses on the tail characteristics of risk loss distribution, and is usually used to analyze rare probability events. It can rely on a small number of sample data to get the change of extreme value in the population distribution when the population distribution is unknown, and has […]

  • Xiecheng


    Original address:time.geekbang.org/column/article/1… Thread implementation model Before we know the difference between coroutine and thread, we might as well understand several ways to implement thread at the bottom, so as to lay a foundation for later learning. There are three ways to implement threads: 1:1 thread model of one-to-one mapping between lightweight process and kernel thread, […]

  • Talk about two state management libraries Redux & recoil of react


    background React is a very excellent UI library. At the beginning, react only focused on the UI layer and did not have a good solution for global state management. Therefore, it gave birth to excellent state management tools such as flux and redux. With the development of time, a number of new state management tools […]

  • Using detectron2 to detect targets in 6 steps


    By akarsh yelitstyCompile FlinSource: to ward data science Let’s see how to use detectron 2 of Fair (Facebook AI research) for instance detection on custom data sets involving text recognition. Have you ever tried to train an object detection model from scratch using a custom dataset of your own choice? If so, you will know […]

  • MTV and MVC model


    MVC and MTV Model 1、MVC MVC is to divide web application into three layers: model (V), controller (c) and view (V); They are connected in a plug-in, loosely coupled way.   M:models Object (ORM) responsible for business object and database   V:views Responsible for interaction with users (page) C: Contonnar controller (routing distribution URLs. Py) Accept the […]

  • A case study of R language penalized logistic regression (Lasso, ridge regression) high dimensional variable selection classification model


    Link to the original text:http://tecdat.cn/?p=21444 Logistic regression is a common method in research, which can screen influencing factors, predict probability and classify. For example, the data obtained by high pass sequencing technology in medical research challenges the selection of high-dimensional variables. Penalized logistic regression can select variables and estimate coefficients for high-dimensional data, and its […]

  • Application of R language multivariate logistic regression


    Original link:http://tecdat.cn/?p=2640   Stepwise regression process can be used to determine multiple logistic regression. This function selects the model to minimize AIC. How to carry out multiple logistic regression Step function can be used to determine multiple logistic regression through stepwise regression process. This function selects the model to minimize AIC. Generally, it is recommended […]

  • Redis internal mechanism


    1. It’s completely memory based. Most requests are pure memory operations, which are very fast. Data is stored in memory, similar to HashMap. The advantage of HashMap is that the time complexity of search and operation is O (1); 2. The data structure is simple and easy to operate. The data structure in redis is […]

  • How to train image classification model in pytorch and tensorflow


    By pulkit SharmaCompile FlinSource: analyticsvidhya introduce Image classification is one of the most important applications of computer vision. Its applications range from object classification from autopilot to recognition of blood cells in medical industry, from identifying defective items in manufacturing industry to establishing systems that can classify people wearing masks or not. In all of […]