Programming VIP

Project introduction: Research on automatic code annotation generation technology based on transformer Introduction: This is my graduation project, which mainly realizes the automatic generation of code comments. Generally speaking, it is to give a piece of code and then generate corresponding comments (functional comments). The data set we u ...

introduction Initially, we will initialize the parameters of the model with the init module. Now we will learn more about how to access and initialize model parameters, and how to share the same model parameters among multiple layers. We first define a multi-layer perceptron with a single hidden layer. We still use the default method to initi ...

CTC introduction This article does not introduce the background and specific application of CTC. The basic knowledge of CTC can be understood through the following articles: Hannun Awni classic blog. General idea Initially, we get an input matrix. Its rows represent time steps with a length of T, and its columns represent the probabiliti ...

Original link: http://tecdat.cn/?p=24761 This document uses some exploratory data analysis to develop the rating curve and flow prediction of the river. The purpose is to create and update rating curves using (1) instantaneous flow measured during periodic deployment of bottom mounted units and (2) instantaneous depth measurements from water le ...

In this rough record about the relevant process. If there are errors, please be an enthusiastic audience in front of the screen and put forward the correct solution I setup script Four words, twists and turns. As a layman of in-depth learning, the environmental configuration and installation in the early stage are quite tossed back and forth, ...

Original text: GBDT+LR CTR estimation - Kaggle example [with data set] - brief book Recently, I read an article on implementing the recommendation system with GBDT+LR and prepared to practice it, but all the articles on this method did not put the data set, so I sorted out my ideas from the beginning and found the data set of Kaggle's last c ...

Graph structure can be seen everywhere in the real world. Roads, social networks and molecular structures can be represented by graphs. Graph is one of the most important data structures we have.There are many resources today that can teach us everything we need to apply machine learning to such data.There have been many theories and materials ...

1. Environment 1.1 create a virtual environment Python 3 7. Install tensorflow GPU = = 1.13 1. Install PIL (PIP install pilot). 1.2 download labelimg, use labelimg to label, save and generate xml files (use these three shortcut keys: ctrl+s to save, d next, w brush tool, and preferably label in string form). 1.3 establish 4 folders (train ...

1, Foreword 🚀 My environment: Locale: Python 3 six point fivecompiler: jupyter notebookDeep learning environment: tensorflow2 four point one 🚀 In depth learning newcomers must see: Introduction to Xiaobai deep learning Xiaobai introduction to in-depth learning Chapter 1: configuring in-depth learning environmentIntroduction to Xiaob ...

Previous episode: Color planet image generation 2: using both traditional Gan discriminator and Markov discriminator (pytorch version) Based on the previous set of code, some detailed modifications are made to improve the generation effect. 1. Modification 1.1 preprocessing scaling The code for preprocessing training set pictures is mod ...