本课程是 TensorFlow: Data and Deployment 专项课程专项课程的一部分

4.3
星
406 个评分

Laurence Moroney

15,294 人已注册

提供方

TensorFlow: Data and Deployment 专项课程deeplearning.ai

课程信息

6,625 次近期查看

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.
In this third course, you will:
- Perform streamlined ETL tasks using TensorFlow Data Services
- Load different datasets and custom feature vectors using TensorFlow Hub and TensorFlow Data Services APIs
- Create and use pre-built pipelines for generating highly reproducible I/O pipelines for any dataset
- Optimize data pipelines that become a bottleneck in the training process
- Publish your own datasets to the TensorFlow Hub library and share standardized data with researchers and developers around the world


This Specialization builds upon our TensorFlow in Practice Specialization. If you are new to TensorFlow, we recommend that you take the TensorFlow in Practice Specialization first. To develop a deeper, foundational understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

可灵活调整截止日期

根据您的日程表重置截止日期。

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 3 门课程（共 4 门）

TensorFlow: Data and Deployment 专项课程

中级

We recommend taking Course 1 of the TensorFlow in Practice Specialization first, or have a basic familiarity with building models in TensorFlow

完成时间大约为16 小时

英语（English）

字幕：阿拉伯语（Arabic）, 法语（French）, （欧洲人讲的）葡萄牙语, 意大利语, 越南语, 德语（German）, 俄语（Russian）, 英语（English）, 西班牙语（Spanish）

您将学到的内容有

Perform efficient ETL tasks using Tensorflow Data Services APIs

Construct train/validation/test splits of any dataset - either custom or present in TensorFlow Hub Dataset library - using Splits API

Use different modules and functions of the TFDS API to prepare your data for training pipelines

Identify bottlenecks in your input pipelines and increase your workflow efficiency by input parallelization

您将获得的技能

Artificial Neural Network
Tensorflow
Extraction, Transformation And Loading (ETL)
Data Pipelines
TensorFlow Datasets

可灵活调整截止日期

根据您的日程表重置截止日期。

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 3 门课程（共 4 门）

TensorFlow: Data and Deployment 专项课程

中级

We recommend taking Course 1 of the TensorFlow in Practice Specialization first, or have a basic familiarity with building models in TensorFlow

完成时间大约为16 小时

英语（English）

授课教师

授课教师评分

4.82/5 （34 个评分）

Laurence Moroney

Instructor

Lead AI Advocate, Google

336,256 个学生

15 门课程

提供方

deeplearning.ai

DeepLearning.AI is an education technology company that develops a global community of AI talent.

授课大纲 - 您将从这门课程中学到什么

内容评分91%（1,073 个评分）

周

周 1

完成时间为 5 小时

Data Pipelines with TensorFlow Data Services

This week, you will be able to perform efficient ETL tasks using Tensorflow Data Services APIs

完成时间为 5 小时

10 个视频（总计 21 分钟）, 4 个阅读材料, 4 个测验

10 个视频

A conversation with Andrew Ng2分钟

Introduction1分钟

Popular Datasets2分钟

Data Pipelines58

Extract, Transform and Load3分钟

Versioning Datasets2分钟

Looking at the Notebook1分钟

Using TFDS in Keras to Train Fashion MNIST 3分钟

Horses or Humans in TFDS2分钟

Week 1 Wrap Up49

4 个阅读材料

Downloading the Ungraded Labs and Programming Assignments10分钟

Try Out the Notebook Yourself10分钟

Try the Horses or Human Notebook10分钟

Grader Note10分钟

1 个练习

Week 1 Quiz30分钟

周

周 2

完成时间为 3 小时

Splits and Slices API for Datasets in TF

In this week, you will construct train/validation/test splits of any dataset - either custom or present in TensorFlow hub dataset library - using Splits API

完成时间为 3 小时

7 个视频（总计 26 分钟）, 3 个阅读材料, 3 个测验

周

周 3

完成时间为 4 小时

Exporting Your Data into the Training Pipeline

This week you will extend your knowledge of data pipelines

完成时间为 4 小时

21 个视频（总计 44 分钟）, 5 个阅读材料, 3 个测验

21 个视频

A Conversation with Andrew Ng1分钟

Introduction22

Input Data1分钟

Basic Mechanics2分钟

Numeric and Bucketized Columns2分钟

Vocabulary and Hashed Columns, Feature Crossing2分钟

Embedding Columns2分钟

Introduction24

Notebook Walkthrough4分钟

Introduction19

Numpy, Pandas and Images2分钟

CSV3分钟

Text and TFRecord1分钟

Generators1分钟

Introduction17

Notebook walkthrough4分钟

Introduction1分钟

Using Numpy and Pandas2分钟

Image Data1分钟

CSV Data4分钟

Text Data2分钟

5 个阅读材料

Link to the Notebook10分钟

Link to the CNN Course10分钟

Link to the Notebook10分钟

CSV Notebook10分钟

Link to the Course 10分钟

1 个练习

Week 3 Quiz30分钟

周

周 4

完成时间为 4 小时

Performance

You'll learn how to handle your data input to avoid bottlenecks, race conditions and more!

完成时间为 4 小时

22 个视频（总计 44 分钟）, 2 个阅读材料, 4 个测验

22 个视频

A conversation with Andrew Ng2分钟

Introduction36

ETL2分钟

What Happens When You Train a Model2分钟

Introduction25

Caching58

Parallelism APIs2分钟

Autotuning2分钟

Parallelizing Data Extraction2分钟

Best Practices for Code Improvements3分钟

A Few Words by Laurence34

A conversation with Andrew Ng1分钟

Introduction44

How to Start Using a Dataset2分钟

Implementation4分钟

File Access and Possible Problems in Data3分钟

Publishing the Dataset3分钟

Introduction18

Going Through the Colab- Part 12分钟

Going Through the Colab - Part 22分钟

Closing Words14

A conversation with Andrew Ng1分钟

2 个阅读材料

URLs10分钟

Link to the Colab10分钟

2 个练习

Week 4 Quiz

Publishing your Dataset Quiz

审阅

4.3

88 条评论

5 stars
62.25%
4 stars
20.58%
3 stars
9.55%
2 stars
4.65%
1 star
2.94%

来自DATA PIPELINES WITH TENSORFLOW DATA SERVICES的热门评论

由 YO 提供May 16, 2020

Debugging exercises due to errors in indentation sounded stupid in the first place. But the joy of finally getting a "yes" in the assignment auto-grader beats them all.

由 PC 提供Apr 16, 2020

I understand why most of the students are furious about, but content wise, it one of those extremely helpful and important courses in Coursera. Really loved it!

由 MI 提供Apr 3, 2020

This course is quite essential, yet it is prepared too quickly? I had a hard time on Week 3 and Week 4 because the exercises are hard to grasp.

由 GL 提供Mar 2, 2020

Laurence cares deeply about the students. Not only about what they learn, but that they actually enjoy and learn it. What a fantastic teacher.

查看所有评论

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.

In this four-course Specialization, you’ll learn how to get your machine learning models into the hands of real people on all kinds of devices. Start by understanding how to train and run machine learning models in browsers and in mobile applications. Learn how to leverage built-in datasets with just a few lines of code, learn about data pipelines with TensorFlow data services, use APIs to control data splitting, process all types of unstructured data, and retrain deployed models with user data while maintaining data privacy. Apply your knowledge in various deployment scenarios and get introduced to TensorFlow Serving, TensorFlow, Hub, TensorBoard, and more. Industries all around the world are adopting Artificial Intelligence. This Specialization from Laurence Moroney and Andrew Ng will help you develop and deploy machine learning models across any device or platform faster and more accurately than ever. Looking for a place to start? Master the foundational basics of TensorFlow with the DeepLearning.AI TensorFlow Developer Professional Certificate. Looking to customize and build powerful real-world models for complex scenarios? Check out the TensorFlow: Advanced Techniques Specialization.

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。
有助学金吗？
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。
Why was Course 3: Data Pipelines with TensorFlow Data Service updated in October 2020?
Changes in TensorFlow API: Since this Specialization was launched in early 2020, there have been changes to the TensorFlow API which affect the material in Weeks 1 and 2. With this refresh, you can access updated lectures, quizzes, and assignments.
Changing the Difficulty Level of Assignments: Based on valuable learner feedback, we’ve revised the Week 4 assignments to ensure that you have a full grasp of the foundational principles and are well-prepared to tackle them.

还有其他问题吗？请访问学生帮助中心。

Data Pipelines with TensorFlow Data Services