The depth of compiler learning starts from zero

0x0. preface The previous articles in this series have a superficial understanding of the components of MLIR. This article will not continue to talk about the architecture of MLIR. But from a practical point of view, let's take readers to see what MLIR has helped me do. Here we still take OneFlow Dialect as an example. stay Interpretation of ...

Added by nicandre on Thu, 10 Mar 2022 17:35:51 +0200

Notes of Web security in-depth learning practice: Chapter 8 harassment message recognition

This chapter mainly takes SMS Spam Collection data set as an example to introduce the identification technology of harassing SMS. This section explains in detail the feature extraction method of harassing SMS with Word2Vec. Word2Vec model 1, Principle Word2Vec is an efficient tool that Google opened in 2013 to represent words as real value v ...

Added by Maracles on Thu, 10 Mar 2022 13:51:35 +0200

How to understand the residual network (resnet) structure and code implementation (pytoch) note sharing

In the network of deep learning, I think the most basic is the residual network. What I share today is not the theoretical part of the residual network. Just remember that the idea of the residual network runs through many network structures behind. If you understand the residual network structure, then some advanced network structures behind a ...

Added by cpharry on Thu, 10 Mar 2022 02:06:36 +0200

[GNN benchmark] Figure benchmark data set of machine learning

Figure ImageNet of neural network? Open source millions of OGB benchmark data sets such as Stanford University In the small data full of "MNIST", does graph neural network also need a big benchmark such as "ImageNet"? Recently, Professor Jure Leskovec of Stanford University announced the open source of Open Graph Benchmar ...

Added by scopley on Wed, 09 Mar 2022 09:47:27 +0200

Surface finishing plan - the third bullet

& & other algorithms 1, Algorithm Given an array of prices, its ith element price [i] represents the price of a given stock on day I. You can only choose to buy this stock one day and sell it on a different day in the future. Design an algorithm to calculate the maximum profit you can make. Return the maximum profit you can make ...

Added by srhino on Wed, 09 Mar 2022 09:29:10 +0200

ROS teb_local_planner use

teb_ local_ The planner is the base of the 2D navigation stack_ local_ Planner plug-in. An online optimized local trajectory planner is implemented to navigate and control mobile robot as a plug-in of ROS navigation package. The initial trajectory generated by the global planner is optimized during runtime to minimize the trajectory execution t ...

Added by cqinzx on Wed, 09 Mar 2022 06:47:21 +0200

Focal Loss upgrade | E-Focal Loss makes Focal Loss dynamic, and the extreme imbalance of categories can be easily solved

Despite the recent success of long tail target detection, almost all long tail target detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more common in the industry because they have a simple and fast Pipeline and are easy to deploy. However, in the case of long tail, this work has not been explore ...

Added by fabby on Wed, 09 Mar 2022 04:11:09 +0200

[mathematical modeling] parking lot simulation system, including Matlab source code

1 Introduction In recent years, with the sustained and rapid development of economy and society and the steady improvement of national living standards, cars have gradually entered the lives of ordinary people. The number of cars in China is increasing. Parking difficulties and traffic jams have appeared in many cities. In order to cope with t ...

Added by k9underdog on Tue, 08 Mar 2022 06:48:54 +0200

XCiT repeats the champion code - the accuracy exceeds the official_ Copy 1

Reprinted from AI Studio Project link https://aistudio.baidu.com/aistudio/projectdetail/3449604 XCiT: covariance image Quansi transformation network This is the fifth issue of the oar paper reproduction challenge< XCiT: Cross-Covariance Image Transformers >The champion code of GitHub is https://github.com/BrilliantYuKaimin/XCiT-PaddlePa ...

Added by jumphopper on Tue, 08 Mar 2022 03:47:55 +0200

Machine translation model three Attention mechanism__ Pytoch implementation

1. Introduction of attention mechanism In the seq2seq model in the previous section, in order to enable the decoder and the linear classification layer to directly obtain more information during decoding, we provide the original context vector to each decoder and the original context vector and word embedding to each linear layer, as shown bel ...

Added by zilem on Tue, 08 Mar 2022 00:42:32 +0200