課程資料
報名日期
全年招生
課程級別
學習模式
修業期
4 小時 56 分鐘
教學語言
英語
授課導師
Mohammed Rijwan
評分
5次瀏覽
課程簡介
Python, Docker, Flask, GitLab, Jenkins tools and technology used for deploy model in your Local server. A complete Guide
Machine Learning Real value comes from actually deploying a machine learning solution into production and the necessary monitoring and optimization work that comes after it.
Most of the problems nowadays as I have made a machine-learning model but what next.
How it is available to the end-user, the answer is through API, but how it works?
How you can understand where the Docker stands and how to monitor the build we created.
This course has been designed to keep these areas under consideration. The combination of industry-standard build pipeline with some of the most common and important tools.
This course has been designed into Following sections:
1) Configure and a quick walkthrough of each of the tools and technologies we used in this course.
2) Building our NLP Machine Learning model and tune the hyperparameters.
3) Creating flask API and running the WebAPI in our Browser.
4) Creating the Docker file, build our image and running our ML Model in Docker container.
5) Configure GitLab and push your code in GitLab.
6) Configure Jenkins and write Jenkins's file and run end-to-end Integration.
This course is perfect for you to have a taste of industry-standard Data Science and deploying in the local server. Hope you enjoy the course as I enjoyed making it.
課程章節
- 6 個章節
- 31 堂課
- 第 1 章 Installation and Configuration
- 第 2 章 Part 1 Natural Language processing Programming
- 第 3 章 Part 2 Programming Python Flask NLP Model
- 第 4 章 Part 3 Introduction to docker commands and Dockerfile
- 第 5 章 CI -CD Pipeline and jenkins configuration
- 第 6 章 Course Completion
課程內容
- Developing the NLP Model for Sentiment analysis and Machine learning deployment on local server using flask and docker.
- Select the most efficient Machine Learning Model,Tune the hyper-parameters and selecting the best model using cross-validation technique
- A quick discussion from the basic in nutshell about DevOps tools like docker, Git and GitLab, Jenkins etc.
- A better understanding about software development and automation in real scenario and concept of end-to-end Integration.
此課程所涵蓋的技能
評價
-
EEugeny
Good one to start with!
-
GGuliyev
poor explanation of contents.
-
AAnthony DiDonato
The intent of the content was intriguing however; it was hard to follow because it seemed to lack structure. The audio was sporadic. If you have basic experience with these tools, you will get through it and find value. Overall the quality of the training delivered and the structure need some work. In the end if you want to understand how to take your ML model to deployment. That mission could be accomplished. Patience was required to sit through every section.
-
NNellie K.
This is an ambitious course: to teach you various deployment pieces in 4 hours, including an hour of building a data science model. As a result, your underlying knowledge of machine learning, virtualisation, docker, Python etc. should already be at least upper-intermediate. Forwarned is forarmed. (the instructor should really change the "pre-requisite" section. It is not just "you have to know a bit of Python"). The delivery is haphazard in places, you have to already have intuition to know what is going on (again, to have the prior knowledge/experience). Giving 4.5 stars still, because I needed to know the deployment with containers/Jenkins and I did get it.
