Buy Now AED 170.99 + VAT

Monthly Subscription Starting at AED 99 + VAT

Data Pipelines with TensorFlow Data Services
  • Level Professional
  • Duration 12 hours
  • Course by DeepLearning.AI
  • Offered by

About

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.

Modules

Data Pipelines with TensorFlow Data Services

    • 1 Videos
Show info about module content

1 Videos

  • A conversation with Andrew Ng

Introduction

    • 6 Videos
    • 3 Readings
Show info about module content

6 Videos

  • Introduction
  • Popular Datasets
  • Data Pipelines
  • Extract, Transform and Load
  • Versioning Datasets
  • Looking at the Notebook

3 Readings

  • Downloading the Ungraded Labs and Programming Assignments
  • [IMPORTANT] Have questions, issues or ideas? Join our Forum!
  • Try Out the Notebook Yourself

Using TFDS

    • 2 Videos
    • 1 Readings
Show info about module content

2 Videos

  • Using TFDS in Keras to Train Fashion MNIST
  • Horses or Humans in TFDS

1 Readings

  • Try the Horses or Human Notebook

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 1

Week1 Quiz and Closing Words

    • 1 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • Week 1 Quiz

1 Videos

  • Week 1 Wrap Up

Exercise 1 - Rock, Paper, Scissors

    • 1 Readings
    • 1 Programming
Show info about module content

1 Programming

  • TFDS with Rock, Paper and Scissors

1 Readings

  • Grader Note

Introduction

    • 1 Videos
Show info about module content

1 Videos

  • Introduction

Splits and Slices

    • 2 Videos
    • 1 Readings
Show info about module content

2 Videos

  • Introduction to Splits API
  • Splits API Notebook Walkthrough

1 Readings

  • Splits API Notebook

TFRecord

    • 3 Videos
    • 1 Readings
Show info about module content

3 Videos

  • File Structure in TensorFlow Datasets
  • Feature Descriptors
  • TFRecord Colab Walkthrough

1 Readings

  • TFRecord Notebook

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 2

Week 2 Quiz and Closing Words

    • 1 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • Week 2

1 Videos

  • Week 2 Wrap Up

Exercise 2

    • 1 Readings
    • 1 Programming
Show info about module content

1 Programming

  • Transfer Learning and Splits API

1 Readings

  • Grader Note

Programming APIs and Column Types

    • 7 Videos
Show info about module content

7 Videos

  • A Conversation with Andrew Ng
  • Introduction
  • Input Data
  • Basic Mechanics
  • Numeric and Bucketized Columns
  • Vocabulary and Hashed Columns, Feature Crossing
  • Embedding Columns

Going over the Notebook

    • 2 Videos
    • 1 Readings
Show info about module content

2 Videos

  • Introduction
  • Notebook Walkthrough

1 Readings

  • Link to the Notebook

Extracting and Loading Data to Pipelines

    • 5 Videos
    • 1 Readings
Show info about module content

5 Videos

  • Introduction
  • Numpy, Pandas and Images
  • CSV
  • Text and TFRecord
  • Generators

1 Readings

  • Link to the CNN Course

Looking at the Code

    • 2 Videos
    • 1 Readings
Show info about module content

2 Videos

  • Introduction
  • Notebook walkthrough

1 Readings

  • Link to the Notebook

Loading Data Present Outside TFDS

    • 5 Videos
    • 2 Readings
Show info about module content

5 Videos

  • Introduction
  • Using Numpy and Pandas
  • Image Data
  • CSV Data
  • Text Data

2 Readings

  • CSV Notebook
  • Link to the Course

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 3

Week 3 quiz

    • 1 Assignment
Show info about module content

1 Assignment

  • Week 3 Quiz

Exercise 3

    • 1 Programming
Show info about module content

1 Programming

  • Classify Structured Data

Tuning and Performance Improvements in your Pipeline

    • 4 Videos
Show info about module content

4 Videos

  • A conversation with Andrew Ng
  • Introduction
  • ETL
  • What Happens When You Train a Model

Methodologies to Improve Performance

    • 5 Videos
Show info about module content

5 Videos

  • Introduction
  • Caching
  • Parallelism APIs
  • Autotuning
  • Parallelizing Data Extraction

Best Practices

    • 2 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • Week 4 Quiz

2 Videos

  • Best Practices for Code Improvements
  • A Few Words by Laurence

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 4

End of Access to Lab Notebooks

    • 1 Readings
Show info about module content

1 Readings

  • [IMPORTANT] Reminder about end of access to Lab Notebooks

Exercise 4

    • 1 Programming
Show info about module content

1 Programming

  • Parallelization with TFDS

[Optional] Publishing your Datasets

    • 6 Videos
    • 1 Readings
Show info about module content

6 Videos

  • A conversation with Andrew Ng
  • Introduction
  • How to Start Using a Dataset
  • Implementation
  • File Access and Possible Problems in Data
  • Publishing the Dataset

1 Readings

  • URLs

[Optional] Colab

    • 4 Videos
    • 1 Readings
    • 1 Lab
    • 1 Assignment
Show info about module content

1 Assignment

  • Publishing your Dataset Quiz

1 Labs

  • Adding a Dataset of your Own to TFDS

4 Videos

  • Introduction
  • Going Through the Colab- Part 1
  • Going Through the Colab - Part 2
  • Closing Words

1 Readings

  • Link to the Colab

Course 3 wrap up

    • 1 Videos
Show info about module content

1 Videos

  • A conversation with Andrew Ng

Auto Summary

Explore the "Data Pipelines with TensorFlow Data Services" course, designed for IT & Computer Science professionals. Led by Coursera, this advanced course delves into efficient ETL tasks, dataset management, and pipeline optimization using TensorFlow tools. Over 720 minutes, you'll learn to create reproducible I/O pipelines and share datasets globally. Ideal for those with TensorFlow experience, various subscription plans are available: Starter, Professional, and Paid. Enhance your data handling skills and streamline your machine learning model deployment.

Laurence Moroney
Instructor

Laurence Moroney