NVIDIA之AI Course：Getting Started with AI on Jetson Nano—Class notes(一)

NVIDIA之AI Course：Getting Started with AI on Jetson Nano—Class notes(一)

导读
        在线参加面向初学者的深度学习研究院课程，可以自由掌握进度。 将学习收集图像数据，并用其为自定义任务（例如识别手势以及用于找到图像中的关键点的图像回归）训练、优化和部署 AI 模型。 甚至可以在 Jetson Nano 上使用 Jupyter Notebooks，借助计算机视觉模型构建深度学习分类项目。
Notice
The original text comes from NVIDIA-AI Course. This article only provides Chinese translation.

Getting Started with AI on Jetson Nano

  • Welcome
  • Setting up your Jetson Nano
  • Image Classification
  • Image Regression
  • Conclusion
  • Feedback

Welcome

Welcome to Getting Started with AI on Jetson Nano! In this course, you will build AI projects on your own NVIDIA® Jetson Nano. You'll learn how to:

  • Set up your Jetson Nano Developer Kit and camera to run this course
  • Collect varied data for image classification projects
  • Train neural network models for classification
  • Annotate image data for regression
  • Train neural network models for regression to localize features
  • Run inference on a live camera feed with your trained models

Working Through The Course

Throughout the course you'll work in two browser windows. The first window is the one you are viewing now. It contains the course pages you'll use for a guided learning experience, hosted on the NVIDIA® Deep Learning Institute (DLI) platform. This is where you'll find instructions, references, and quizzes. You can also track your progress toward earning a Certificate of Competency for the course.
      The second browser window contains a remote JupyterLab interface into your Jetson Nano. You'll begin with some hardware setup in the Setting up your Jetson Nano section, and then open this window in your computer browser. This JupyterLab window is where you'll run Python code interactively in Jupyter notebooks to view the camera feed and build your AI Classification and Regression projects. The Jupyter notebooks you'll work with are easy to copy, change, experiment with, and extend for your own additional projects whenever you are ready to do so!
      Let's get started! The following video provides a brief overview of the Jetson Nano Developer Kit product.

在整个课程中，您将在两个浏览器窗口中工作。第一个窗口是您现在正在查看的窗口。它包含在Nvidia®深度学习学院（DLI）平台上举办的引导式学习体验课程页面。在这里您可以找到说明、参考资料和测验。您还可以跟踪您获得课程合格证书的进度。
         第二个浏览器窗口在Jetson nano中包含远程jupyterlab界面。您将从设置Jetson nano部分中的一些硬件设置开始，然后在计算机浏览器中打开此窗口。在这个jupyterlab窗口中，您将在jupyter笔记本中交互运行python代码，以查看摄像头提要并构建人工智能分类和回归项目。你将要使用的Jupyter笔记本很容易复制、更改、实验，并且在你准备好的时候扩展到你自己的附加项目中。
         我们开始吧！以下视频简要概述了Jetson nano开发工具包产品。

Course Outline课程大纲

The course consists of three main sections. Use the navigation and breadcrumb links at the top of each section to step through the lessons.
该课程由三个主要部分组成。使用每个部分顶部的导航和breadcrumb链接来逐步完成课程。

1. Setting Up Your Jetson Nano
Step-by-step guide to set up your hardware and software for the course projects
一步一步的指导，设置您的硬件和软件的课程项目。

  • Introduction：What's included with the Jetson Nano Developer Kit
  • Prepare for Setup：Descriptions of additional hardware you need to get started
  • Write Image to the MicroSD Card：How to download the software for this course and make it available to the Jetson Nano Developer Kit
  • Setup and First Boot：Illustrated step-by-step instructions to boot your Jetson Nano with the complete OS image and course software
  • Camera Setup：How to connect your camera to the Jetson Nano Developer Kit
  • Hello Camera：How to test your camera with an interactive Jupyter notebook on the Jetson Nano Developer Kit
  • JupyterLab：A brief introduction to the JupyterLab interface and notebooks

2. Image Classification图像分类
Background information and instructions to create projects that classify images using Deep Learning
创建使用深度学习对图像进行分类的项目的背景信息和说明。

  • AI and Deep Learning：A brief overview of Deep Learning and how it relates to Artificial Intelligence (AI)
  • Convolutional Neural Networks (CNNs)：An introduction to the dominant class of artificial neural networks for computer vision tasks
  • ResNet-18：Specifics on the ResNet-18 network architecture used in the class projects
  • Thumbs Project：Work with the Interactive Classification notebook to create your first project
  • Emotions Project：Build a new project with the same Interactive notebook to detect emotions from facial expressions.建立一个新的项目相同的交互式笔记本检测情绪面部表情。
  • Quiz Questions：Answer questions about what you've learned to reinforce your knowledge.回答问题对你所学到的知识巩固你的知识

3. Image Regression 图像回归
Instructions to create projects that can localize and track image features in a live camera image. 介绍创建一个项目，可以本地化和跟踪实时摄像机图像中的图像功能。

  • Classification vs. Regression：With a few changes, your the Classification model can be converted to a Regression model.用一些小的改变，你的分类模型可以转化成一个回归模型。
  • Face XY Project：Build a project that finds the coordinates of facial features.建立一个项目,发现面部特征的坐标
  • Quiz Questions：Answer questions about what you've learned to reinforce your knowledge.回答问题对你所学到的知识巩固你的知识
赞 (0)

相关推荐