ORB-SLAM2 from theory to code implementation: ORB feature extraction and matching theory and code explanation

1. Theoretical knowledge Feature points are composed of key points and descriptors. ORB feature points (Oriented FAST and Rotated BRIEF) are composed of Oriented FAST corner points and BRIEF (binary robot independent elemental features) descriptors. Its calculation speed is 100 times that of sift feature points and 10 times that of surf featur ...

Added by frans-jan on Fri, 18 Feb 2022 12:23:25 +0200

Using out of pocket prediction (oof) to evaluate the generalization performance of the model and build an integrated model

Machine learning algorithms usually use cross validation techniques such as kFold to improve the accuracy of the model. In the process of cross validation, the prediction is carried out through the split test set that is not used for model training. These predictions are called out of fold predictions. External prediction plays an important rol ...

Added by gOloVasTicK on Fri, 18 Feb 2022 10:22:40 +0200

Tensorflow model saving, loading and fine tune

1, Save Tensorflow model: 1. Save file description Tensorflow model mainly includes the design (diagram) of the network and the values of trained parameters. Therefore, tensorflow model has two main files: 1) graph.pbtxt: This is actually a text file, which saves the structure information of the model 2) checkpoint file: in fact, it is a tx ...

Added by oeb on Fri, 18 Feb 2022 08:08:45 +0200

Analysis of minimax search algorithm and α-β Pruning algorithm (with case and complete code)

preface First I did a small project of Gobang, and then I did a more powerful project of Chinese chess, but I never realized a version of "intelligent" AI. It is well known that the bottom layer of ai algorithm for this kind of game problem is to use minimax search algorithm and α-β Pruning pruning optimization, but I ...

Added by kippi on Thu, 17 Feb 2022 22:16:51 +0200

Detailed explanation and code implementation of soft voting and hard voting mechanism in integrated learning

Quickly review the soft voting and hard voting in the integration methodThe integration method is to combine the results of two or more separate machine learning algorithms and try to produce more accurate results than any single algorithm.In soft voting, the probability of each category is averaged to produce results. For example, if algorithm ...

Added by cavendano on Thu, 17 Feb 2022 04:26:42 +0200

Pytoch: fast migration of image style

Pytoch: fast migration of image style - residual network, fixed style and arbitrary content Copyright: Jingmin Wei, Pattern Recognition and Intelligent System, School of Artificial and Intelligence, Huazhong University of Science and Technology Pytoch tutorial column link This tutorial is not for commercial use. It is only for learning ...

Added by idire on Wed, 16 Feb 2022 20:03:05 +0200

Pytorch: image style migration

Pytoch: image style migration Copyright: Jingmin Wei, Pattern Recognition and Intelligent System, School of Artificial and Intelligence, Huazhong University of Science and Technology Reference Image Style Transfer Using Convolutional Neural Networks A Neural Algorithm of Artistic Style Perceptual Losses for Real-Time Style Transfer a ...

Added by FirePhoenix on Wed, 16 Feb 2022 19:52:14 +0200

Use python to convert long video and long voice into text tutorial, which is very easy to use

Originally, I wanted to make a voice to text, but I found that many blogs didn't say what I wanted. The reasons are as follows: 1. Because the voice supported by Baidu interface is pcm format, and my own is mp3 format file. 2. Baidu only supports the file format within 60s, and what it wants is a long file, and hopes to cut it into 60s to meet ...

Added by adsegzy on Wed, 16 Feb 2022 10:50:21 +0200

Federal learning: dividing non IID samples according to Dirichlet distribution

Python wechat ordering applet course video https://edu.csdn.net/course/detail/36074 Python actual combat quantitative transaction financial management system https://edu.csdn.net/course/detail/35475 We are Random sampling and probability distribution in Python (II) This paper introduces how to sample a probability distribution with Python's ...

Added by nipsilanti on Wed, 16 Feb 2022 00:20:59 +0200

Machine learning - Data Science Library Day 3 - Notes

What is numpy A basic library for scientific calculation in Python, which focuses on numerical calculation. It is also the basic library of most Python scientific calculation libraries. It is mostly used to perform numerical operations on large and multi-dimensional arrays Axis In numpy, it can be understood as direction, which is expres ...

Added by wrequed on Tue, 15 Feb 2022 17:12:50 +0200