Use modelarts quickly, zero base white can also play AI!
2020-11-06 20:12:20 【Huawei cloud developer community】
Abstract ： Pass by don't miss , see Copy How can siege lions use Huawei cloud ModelArts Get along well with AI.
“ since 2018 year 10 Since month ,ModelArts It has served hundreds of thousands of developers in many industries , Through the completeness of the basic platform, industry-oriented knowledge precipitation and platform ability , bring AI Application development is simpler and more efficient .”
Just as Xu Zhijun, Huawei's chairman in office, is in 《ModelArts Artificial intelligence application development guide 》 The preface in a book mentions ,ModelArts To simplify the AI Application development process 、 To optimize the AI The development cost of the application 、 To reduce the AI Industry application development skills requirements . For zero base partners , How to get started quickly AI application development ？ I'm sure you'll learn to use ModelArts The experience of , You should be able to find the answer .
to encounter ModelArts
When it comes to bonding ModelArts, I have to tell you the story of Huawei cloud . Last year , Develop mobile application for Party A's father , their APP Distributed through Huawei application market , So I registered with Huawei developer account . meanwhile , I'm keen to participate in offline technology exchange activities in front-end development , By chance, I was lucky to get “HDC2019” Tickets for Huawei Developer Conference , The first focus is on front-end technology , For example, when I went to Songshan Lake in Dongguan, I was aiming at Huawei's fast application . stay HDC At the conference , What impresses me most is CodeLab, Similar to offline workshops , From the most basic “Hello World” Start , It makes it easy for developers to understand and accept a new technology . I remember that I was involved in several CodeLab, Basically, they are biased towards front-end development , Such as fast application development 、AppGallery Connect、 Mobile theme development, etc …… Of course , at present CodeLab Also a development guide on the wire , Such as ：0 Code development image classification AI Model ; There are more convenient sandbox labs , For we can experience the use of ModelArts Realize flower image classification 、 be based on ModelArts Realize face recognition and other practical operations .
But after that , I've always focused on technology sharing in the front end , Like Huawei cloud “7 Day play front-end R & D training camp ”…… Although the first contact with Huawei cloud did not directly encounter ModelArts, But for the later encounter did a lot of bedding . This year, 4 Month of the month , In the forum, I happened to pay attention to MDG Host 《 innovation AI Activities ： After reading the epidemic prevention class under cherry blossom in Wuhan University 》 And Mr. Mao Qichang 【AI Innovation developer Salon 】 How to use Huawei cloud ModelArts Realize strawberry ripening recognition ？, It is preliminarily understood that with the help of Huawei cloud one-stop AI Development platform ModelArts, Zero basis can also be developed such as image classification 、 Object detection 、 Predictive analysis 、 Sound classification 、 Text classification, etc AI application development ; Then he also participated in Huawei cloud developers AI Youth class hacksong competition , First time, I started to adjust my participation , But it's zero basis after all , Through constant attempts , Finally, the baseline code is tuned to 0.948, And put this paragraph “ Keep hitting the wall ” The experience of sharing ModelArts Block , So I was in ModelArts The first post of the section --《【 Touch and learn ModelArts】 Easy to finish Baseline And tune to 0.》, Later, I joined Huawei cloud AI Combat camp , I'm lucky to share my learning ModelArts In process “copy Experience ”, Completed the first live broadcast of life --【AI Actual classroom 】2020 Time for clouds AI Combat camp ——FasterRCNN and YoLoV3 The algorithm completes the object detection , And then it was really out of control , I fell in love with ModelArts. She taught me ：AI, It's not that hard ; learn AI Just arrive huaweicloud.ai!
Before learning any knowledge or skill , I think we have to ask ourselves first , Why study ？ For example, why should we learn ModelArts？ To me, , The idea is simple ： Today, , Artificial intelligence seems to be integrated into daily life , There are only two kinds of people in the future -- One that makes money with artificial intelligence , One is for artificial intelligence consumption ; As front-end Copy Siege lions , If there can be AI Hold up automatic Copy Code is like a fish in water , Isn't it fun ？ Today this one doesn't have AI The mobile phone supported by chip can't be called “ Flagship machine ” Era , No, AI The siege lions with bonus skills feel a little out of date . however , When it comes to learning artificial intelligence , The first thing you may think of is that technology is too difficult 、 be unable to learn how to do sth. . If , You've experienced one stop AI Development platform ModelArts, You will be as surprised as I am ： original AI Development can be so simple ？
Then how to learn ModelArts Well ？ According to my past experience , I feel that no matter what new knowledge or skills are learned , Official documents are the most original learning materials . for instance , I want to learn the whole scene deep learning framework MindSpore, Then I may visit MindSpore Its official website --https://www.mindspore.cn/, We can easily find documents 、 course 、 Code and even teaching videos of handlebars . More Than This , We can also easily find ways to join the community and find good friends who share the same ideals and move forward together .
Empathy , To learn ModelArts, The first step is to get to know her , First of all, the official website went a wave ：ModelArts It's built by Huawei cloud , visit Hua Wei Yun ModelArts Prefecture and Hua Wei Yun AI Community You can find it easily ModelArts And AI Related tutorials . such as , We can get AI Developer growth path , from 0 To 1 Become AI Development talent .
In addition to official documentation and tutorials , We can focus on MDG（ModelArts Developer community ）、 Hua Wei Yun ModelArts Forums and blogs , The latest first-hand information can be obtained in time , Such as ModelArts New features 、 Official activities and wonderful sharing by community partners . secondly , Learn to ModelArts The best way to do it yourself is to do it yourself , Early learning , We can learn some basic concepts and operations according to the official documents , Then we can try to practice our own ideas , For example, Mr. Zhu Yongchun shared many creative practices before , Yes Milk tea recognition 、 Yes A fancy confession 、 Yes Cloud graduation photos are generated . Of course , Being willing to share also contributes to your own improvement , Sharing is also a catalyst for learning , Looking forward to seeing your sharing 、 Learn together and progress together ！
I don't say much nonsense , On the first one “Hello ModelArts” Case study -- Look for yunbao （ Using automatic learning to achieve object detection applications , Yunbao is the mascot of Huawei cloud ）, I hope to do some short exercises by myself , You can feel the use of ModelArts Development AI How simple is the application .
0. Environmental preparation
First time experience ModelArts Before , It is necessary to register Huawei cloud account and conduct real name authentication ;ModelArts The service , You need to configure the global settings first , You can delegate ModelArts visit OBS、SWR、IEF Wait for services to be relied on , With delegation, you can control the scope of authorization more finely , Or by configuring the access key for authorization . This case also needs data storage service OBS, May refer to ModelArts preparation .
1. Data set preparation
Thanks to the ModelArts Powerful AI Data set sharing provided by the market , I have uploaded the dataset of this practice , Simply visit ModelArts AI Market data set module , Search for “Yunbao”, You can find some marked yunbao image data sets . adopt AI Distribution of market dataset module , We can download the dataset directly to our own ModelArts in . Through data set management, you can directly manage from AI It was downloaded from the market ModelArts Data sets , In this way, there is no need to download the dataset locally and then upload it to OBS We've created a new dataset , Greatly simplifies the development process .
2. Data tagging
Based on the dataset downloaded in the previous step , We can create a new automatic learning - Object detection task , Data annotation in the task ; It can also be done in data management - Select the data set downloaded in the previous step for annotation . Of course , If you want to experience automatic grouping 、 Intelligent annotation and other data set advanced operations , It is suggested to use the second way , After labeling, synchronize the data in the automatic learning task .
Due to the fact that part of the data provided in this practice has been marked , So we can train directly , But the results of the training are not as good as all the marks . Creating training is also very simple , Softly ,ModelArts And then we started to train automatically , Just wait a moment .
The following figure V001 It's just marked 26 The training results of the pictures in ,V002 It's all marked training results . The difference is very obvious , Of course, the training time difference is quite big , All marked training hours are almost the same 2 times , But in return for a significant improvement in accuracy , It's also worth it .
Deployment is one click , Here I am. V002 This version is based on online deployment , Still waiting for a moment , The service can be called when it runs normally . I have to praise it here ,ModelArts It still provides a free online deployment service instance , It further reduces our development of AI Cost of .
Just debug it , Basically, it can accurately identify yunbao and its location , So far, zero code development object detection AI The model is done , you Get Have we arrived ？ Is it right? So easy？
Explore happiness , Share happiness
Just learning ModelArts When , There's a little thought ： I organized my learning experience into documents or videos to share, helping more partners to understand and learn ModelArts, Even published a comprehensive study ModelArts E-book tutorial for …… However , A few months passed , My thoughts are just ideas , The official development guide has indeed been published ！ however , The idea is still in my mind , More detailed tutorials still need to be polished , There are still small goals -- Learn and sort out in the next year 《 Touch and learn ModelArts》 e-book , First blow out the cowhide .
Looking back on the past few months of study , except AI The combat camp insists on clocking in and sharing , be based on ModelArts And the bank's front-end development , I experienced one stop AI Development ： be based on ModelArts Official case completed bank deposit forecast small Demo, See 【 Touch and learn ModelArts】 Did you make a deposit today ？; be based on AI The named entity recognition case of the combat camp completes Huawei cloud application magic cube AppCube And ModelArts The exploration of combination , See 【Copy The City lion log 】ModelArts And AppCube double “ magic ” A couple of festivals . It's not very technical , It's not climate , But it's also one step at a time , Study and explore in a down-to-earth manner , At the same time, thank you for your love , It's really worth it , Very happy .
besides , I'm also keen on giving ModelArts Sample code base document error correction , It's true “ Document modification contributor ”; Of course, by learning ModelArts-Labs The code base , It is also the first time to master ModelArts New play ; If you can go beyond learning , And help other kids by the way , Why not do it ？
-  Sandbox lab : https://lab.huaweicloud.com/
-  Use ModelArts Realize flower image classification : https://lab.huaweicloud.com/testdetail.html?testId=287
-  be based on ModelArts Face recognition is realized : https://lab.huaweicloud.com/testdetail.html?testId=337
- 《 innovation AI Activities ： After reading the epidemic prevention class under cherry blossom in Wuhan University 》: https://bbs.huaweicloud.com/forum/forum.php?mod=viewthread&tid=49066
- 【AI Innovation developer Salon 】 How to use Huawei cloud ModelArts Realize strawberry ripening recognition ？: https://bbs.huaweicloud.com/forum/forum.php?mod=viewthread&tid=51063
-  Huawei cloud Developer AI Youth class hacksong competition : https://competition.huaweicloud.com/information/1000040170/introduction?track=111
- 《【 Touch and learn ModelArts】 Easy to finish Baseline And tune to 0.》: https://bbs.huaweicloud.com/forum/thread-53839-1-1.html
- 【AI Actual classroom 】2020 Time for clouds AI Combat camp ——FasterRCNN and YoLoV3 The algorithm completes the object detection : https://bbs.huaweicloud.com/videos/102783
-  MindSpore: https://www.mindspore.cn/
-  Modelarts: https://www.huaweicloud.com/product/modelarts.html
-  Hua Wei Yun AI Community : http://huaweicloud.ai/
-  Milk tea recognition : https://bbs.huaweicloud.com/blogs/163274
-  A fancy confession : https://bbs.huaweicloud.com/blogs/159114
-  Cloud graduation photos are generated : https://bbs.huaweicloud.com/blogs/174983
- 【 Touch and learn ModelArts】 Did you make a deposit today ？: https://bbs.huaweicloud.com/forum/thread-63090-1-1.html
- 【Copy The City lion log 】ModelArts And AppCube double “ magic ” A couple of festivals : https://bbs.huaweicloud.com/blogs/198313
-  ModelArts-Labs: https://github.com/huaweicloud/ModelArts-Lab
本文为[Huawei cloud developer community]所创，转载请带上原文链接，感谢
- C++ 数字、string和char*的转换
- Won the CKA + CKS certificate with the highest gold content in kubernetes in 31 days!
- C + + number, string and char * conversion
- C + + Learning -- capacity() and resize() in C + +
- C + + Learning -- about code performance optimization
C + + programming experience (6): using C + + style type conversion
Latest party and government work report ppt - Park ppt
Online ID number extraction birthday tool
Field pointer? Dangling pointer? This article will help you understand!
GVRP of hcna Routing & Switching
- LeetCode 91. 解码方法
- Seq2seq implements chat robot
- [chat robot] principle of seq2seq model
- Leetcode 91. Decoding method
- HCNA Routing＆Switching之GVRP
- GVRP of hcna Routing & Switching
- HDU7016 Random Walk 2
- [Code+＃1]Yazid 的新生舞会
- CF1548C The Three Little Pigs
- HDU7033 Typing Contest
- HDU7016 Random Walk 2
- [code + 1] Yazid's freshman ball
- CF1548C The Three Little Pigs
- HDU7033 Typing Contest
- Qt Creator 自动补齐变慢的解决
- HALCON 20.11：如何处理标定助手品质问题
- HALCON 20.11：标定助手使用注意事项
- Solution of QT creator's automatic replenishment slowing down
- Halcon 20.11: how to deal with the quality problem of calibration assistant
- Halcon 20.11: precautions for use of calibration assistant
- "Top ten scientific and technological issues" announced| Young scientists 50 ² forum
- Reverse linked list
- JS data type
- Remember the bug encountered in reading and writing a file
- Singleton mode
- 在这个 N 多编程语言争霸的世界，C++ 究竟还有没有未来？
- In this world of N programming languages, is there a future for C + +?
- js Promise
- js 数组方法 回顾
- ES6 template characters
- js Promise
- JS array method review
- 【Golang】️走进 Go 语言️ 第一课 Hello World
- [golang] go into go language lesson 1 Hello World