Bringing a machine learning model into the real world involves a lot more than just modeling. This Specialization will teach you how to navigate various deployment scenarios and use data more effectively to train your model.
提供方
TensorFlow: Data and Deployment 专项课程deeplearning.ai课程信息
74,076 次近期查看
可分享的证书
完成后获得证书
100% 在线
立即开始，按照自己的计划学习。
第 1 门课程（共 4 门）
可灵活调整截止日期
根据您的日程表重置截止日期。
中级
Basic understanding of JavaScript
完成时间大约为18 小时
英语（English）
字幕：英语（English）
您将学到的内容有
Train and run inference in a browser
Handle data in a browser
Build an object classification and recognition model using a webcam
您将获得的技能
Convolutional Neural NetworkMachine LearningTensorflowObject DetectionTensorFlow.js
可分享的证书
完成后获得证书
100% 在线
立即开始，按照自己的计划学习。
第 1 门课程（共 4 门）
可灵活调整截止日期
根据您的日程表重置截止日期。
中级
Basic understanding of JavaScript
完成时间大约为18 小时
英语（English）
字幕：英语（English）
提供方
deeplearning.ai
Founded by Andrew Ng, DeepLearning.AI is an education technology company that develops a global community of AI talent.
教学大纲 - 您将从这门课程中学到什么
完成时间为 5 小时
Introduction to TensorFlow.js
Welcome to Browser-based Models with TensorFlow.js, the first course of the TensorFlow for Data and Deployment Specialization. In this first course, we’re going to look at how to train machine learning models in the browser and how to use them to perform inference using JavaScript. This will allow you to use machine learning directly in the browser as well as on backend servers like Node.js. In the first week of the course, we are going to build some basic models using JavaScript and we'll execute them in simple web pages.
完成时间为 5 小时
11 个视频 （总计 30 分钟）, 7 个阅读材料, 3 个测验
11 个视频
Course Introduction, A Conversation with Andrew Ng1分钟
A Few Words From Laurence2分钟
Building the Model3分钟
Training the Model3分钟
First Example In Code4分钟
The Iris Dataset1分钟
Reading the Data4分钟
One-hot Encoding1分钟
Designing the NN2分钟
Iris Classifier In Code6分钟
7 个阅读材料
Getting Your System Ready10分钟
Downloading the Coding Examples and Exercises10分钟
Your First Model10分钟
Iris Dataset Documentation10分钟
Using the Web Server10分钟
Iris Classifier10分钟
Week 1 Wrap up10分钟
2 个练习
Quiz 1
One-Hot Encoding
完成时间为 4 小时
Image Classification In the Browser
This week we'll look at Computer Vision problems, including some of the unique considerations when using JavaScript, such as handling thousands of images for training. By the end of this module you will know how to build a site that lets you draw in the browser and recognizes your handwritten digits!
完成时间为 4 小时
8 个视频 （总计 27 分钟）, 5 个阅读材料, 2 个测验
8 个视频
Creating a Convolutional Net with JavaScript4分钟
Visualizing the Training Process2分钟
What Is a Sprite Sheet?1分钟
Using the Sprite Sheet2分钟
Using tf.tidy() to Save Memory1分钟
A Few Words From Laurence24
MNIST Classifier In Code13分钟
5 个阅读材料
tjs-vis Documentation10分钟
MNIST Sprite Sheet10分钟
MNIST Classifier10分钟
Week 2 Wrap up10分钟
Exercise Description10分钟
1 个练习
Week 2 Quiz
完成时间为 5 小时
Converting Models to JSON Format
This week we'll see how to take models that have been created with TensorFlow in Python and convert them to JSON format so that they can run in the browser using Javascript. We will start by looking at two models that have already been pre-converted. One of them is going to be a toxicity classifier, which uses NLP to determine if a phrase is toxic in a number of categories; the other one is Mobilenet which can be used to detect content in images. By the end of this module, you will train a model in Python yourself and convert it to JSON format using the tensorflow.js converter.
完成时间为 5 小时
12 个视频 （总计 28 分钟）, 7 个阅读材料, 2 个测验
12 个视频
A Few Words From Laurence1分钟
Pre-trained TensorFlow.js Models49
Toxicity Classifier3分钟
Toxicity Classifier In Code3分钟
MobileNet49
Using MobileNet1分钟
Training Results1分钟
MobileNet Example In Code3分钟
Converting Models to JavaScript4分钟
Converting Models to JavaScript In Code2分钟
Linear Example In Code1分钟
7 个阅读材料
Important Links10分钟
Toxicity Classifier10分钟
Classes Supported by MobileNet10分钟
Image Classification Using MobileNet10分钟
Linear Model10分钟
Week 3 Wrap up10分钟
Optional - Install Wget (Only If Needed)10分钟
1 个练习
Week 3 Quiz
完成时间为 4 小时
Transfer Learning with Pre-Trained Models
One final work type that you'll need when creating Machine Learned applications in the browser is to understand how transfer learning works. This week you'll build a complete web site that uses TensorFlow.js, capturing data from the web cam, and re-training mobilenet to recognize Rock, Paper and Scissors gestures.
完成时间为 4 小时
11 个视频 （总计 26 分钟）, 3 个阅读材料, 2 个测验
11 个视频
A Few Words From Laurence53
Building a Simple Web Page2分钟
Retraining the MobileNet Model1分钟
The Training Function2分钟
Capturing the Data3分钟
The Dataset Class2分钟
Training the Network with the Captured Data1分钟
Performing Inference4分钟
Rock Paper Scissors In Code4分钟
A Conversation with Andrew Ng1分钟
3 个阅读材料
Rock Paper Scissors10分钟
Exercise Description10分钟
Wrap up10分钟
1 个练习
Week 4 Quiz
审阅
来自BROWSER-BASED MODELS WITH TENSORFLOW.JS的热门评论
由 AZ 提供Mar 28, 2020
No doubt, the team of Deeplearning.AI is building best learning resources. We would love to get more and more resources for easy way learning from DeepLearning.AI Team. Thanks to all.
由 SA 提供Jul 7, 2020
course contents are good and explained very well with one problem of audio, audio is not clear and pitch is low but I like this course. as a beginner, this course is best.
由 ZB 提供Dec 19, 2019
Awesome - elegant in its complex simplicity. Clear explanations, logical curriculum structure, nice and knowledgeable code examples. A must-complete course indeed!
由 DP 提供Jul 3, 2020
Excellent presentation of material and lab examples. Final assignment is really inspiring and motivating. Thank you for putting effort to design such content.
关于 TensorFlow: Data and Deployment 专项课程
Continue developing your skills in TensorFlow as you learn to navigate through a wide range of deployment scenarios and discover new ways to use data more effectively when training your machine learning models.
常见问题
我什么时候能够访问课程视频和作业？
讲座和作业的访问权限取决于您的注册类型。如果您以旁听模式参加课程，则可以免费查看大多数课程资料。要访问评分作业并获得证书，您需要在旁听期间或之后购买证书体验。如果看不到旁听选项：
- 课程可能不提供旁听选项。您可以尝试免费试用，也可以申请助学金。
- 课程可能会改为提供'完整课程，没有证书'。通过此选项，您可以查看所有课程材料、提交所要求的作业，以及获得最终成绩。这也意味着您将无法购买证书体验。
我订阅此专项课程后会得到什么？
您注册课程后，将有权访问专项课程中的所有课程，并且会在完成课程后获得证书。您的电子课程证书将添加到您的成就页中，您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容，可以免费旁听课程。
Is financial aid available?
是的，Coursera 可以为无法承担费用的学生提供助学金。通过点击左侧“注册”按钮下的“助学金”链接可以申请助学金。您可以根据屏幕提示完成申请，申请获批后会收到通知。您需要针对专项课程中的每一门课程完成上述步骤，包括毕业项目。了解更多。
完成课程后，我会获得大学学分吗？
此课程不提供大学学分，但部分大学可能会选择接受课程证书作为学分。查看您的合作院校，了解详情。Coursera 上的在线学位和 Mastertrack™ 证书提供获得大学学分的机会。
还有其他问题吗？请访问 学生帮助中心。
