Este curso forma parte de Programa Especializado - TensorFlow: Data and Deployment

Laurence Moroney

ofrecido por

Programa Especializado - TensorFlow: Data and Deploymentdeeplearning.ai

Acerca de este Curso

48,929 vistas recientes

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.

Certificado para compartir

Obtén un certificado al finalizar

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Curso 3 de 4 en

Programa Especializado - TensorFlow: Data and Deployment

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Nivel intermedio

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

Aprox. 11 horas para completar

Inglés (English)

Subtítulos: Inglés (English)

Qué aprenderás

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

Habilidades que obtendrás

Artificial Neural NetworkTensorflowExtraction, Transformation And Loading (ETL)Data PipelinesTensorFlow Datasets

Certificado para compartir

Obtén un certificado al finalizar

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Curso 3 de 4 en

Programa Especializado - TensorFlow: Data and Deployment

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Nivel intermedio

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

Aprox. 11 horas para completar

Inglés (English)

Subtítulos: Inglés (English)

Instructor

Calificación del instructor

4.73/5 (15 calificaciones)

Laurence Moroney

ofrecido por

deeplearning.ai

Founded by Andrew Ng, DeepLearning.AI is an education technology company that develops a global community of AI talent.

Programa - Qué aprenderás en este curso

Semana

Semana 1

3 horas para completar

Data Pipelines with TensorFlow Data Services

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

3 horas para completar

10 videos (Total 21 minutos), 4 lecturas, 2 cuestionarios

10 videos

A conversation with Andrew Ng2m

Introduction1m

Popular Datasets2m

Data Pipelines58s

Extract, Transform and Load3m

Versioning Datasets2m

Looking at the Notebook1m

Using TFDS in Keras to Train Fashion MNIST 3m

Horses or Humans in TFDS2m

Week 1 Wrap Up49s

4 lecturas

Downloading the Coding Examples and Exercises10m

Try Out the Notebook Yourself10m

Try the Horses or Human Notebook10m

Grader Note10m

1 ejercicio de práctica

Week 1 Quiz30m

Semana

Semana 2

2 horas para completar

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

2 horas para completar

7 videos (Total 26 minutos), 3 lecturas, 2 cuestionarios

7 videos

Introduction1m

Introduction to Splits API5m

Splits API Notebook Walkthrough5m

File Structure in TensorFlow Datasets1m

Feature Descriptors4m

TFRecord Colab Walkthrough5m

Week 2 Wrap Up1m

3 lecturas

Splits API Colab10m

TFRecord Colab 10m

Grader Note10m

1 ejercicio de práctica

Week 230m

Semana

Semana 3

3 horas para completar

Exporting Your Data into the Training Pipeline

This week you will extend your knowledge of data pipelines

3 horas para completar

21 videos (Total 44 minutos), 5 lecturas, 2 cuestionarios

21 videos

A Conversation with Andrew Ng1m

Introduction22s

Input Data1m

Basic Mechanics2m

Numeric and Bucketized Columns2m

Vocabulary and Hashed Columns, Feature Crossing2m

Embedding Columns2m

Introduction24s

Notebook Walkthrough4m

Introduction19s

Numpy, Pandas and Images2m

CSV3m

Text and TFRecord1m

Generators1m

Introduction17s

Notebook walkthrough4m

Introduction1m

Using Numpy and Pandas2m

Image Data1m

CSV Data4m

Text Data2m

5 lecturas

Link to the Notebook10m

Link to the CNN Course10m

Link to the Notebook10m

CSV Colab10m

Link to the Course 10m

1 ejercicio de práctica

Week 3 Quiz30m

Semana

Semana 4

3 horas para completar

Performance

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

3 horas para completar

22 videos (Total 44 minutos), 2 lecturas, 3 cuestionarios

22 videos

A conversation with Andrew Ng2m

Introduction36s

ETL2m

What Happens When You Train a Model2m

Introduction25s

Caching58s

Parallelism APIs2m

Autotuning2m

Parallelizing Data Extraction2m

Best Practices for Code Improvements3m

A Few Words by Laurence34s

A conversation with Andrew Ng1m

Introduction44s

How to Start Using a Dataset2m

Implementation4m

File Access and Possible Problems in Data3m

Publishing the Dataset3m

Introduction18s

Going Through the Colab- Part 12m

Going Through the Colab - Part 22m

Closing Words14s

A conversation with Andrew Ng1m

2 lecturas

URLs10m

Link to the Colab10m

2 ejercicios de práctica

Week 4 Quiz

Publishing your Dataset Quiz

Acerca de Programa especializado: TensorFlow: Data and Deployment

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. This Specialization builds upon skills learned in the TensorFlow in Practice Specialization. We recommend learners complete that Specialization prior to enrolling in TensorFlow: Data and Deployment.

Preguntas Frecuentes

¿Cuándo podré acceder a las lecciones y tareas?
El acceso a las clases y las asignaciones depende del tipo de inscripción que tengas. Si tomas un curso en modo de oyente, verás la mayoría de los materiales del curso en forma gratuita. Para acceder a asignaciones calificadas y obtener un certificado, deberás comprar la experiencia de Certificado, ya sea durante o después de participar como oyente. Si no ves la opción de oyente:
es posible que el curso no ofrezca la opción de participar como oyente. En cambio, puedes intentar con una Prueba gratis o postularte para recibir ayuda económica.
Es posible que el curso ofrezca la opción 'Curso completo, sin certificado'. Esta opción te permite ver todos los materiales del curso, enviar las evaluaciones requeridas y obtener una calificación final. También significa que no podrás comprar una experiencia de Certificado.
¿Qué recibiré si me suscribo a este Programa especializado?
Cuando te inscribes en un curso, obtienes acceso a todos los cursos que forman parte del Programa especializado y te darán un Certificado cuando completes el trabajo. Se añadirá tu Certificado electrónico a la página Logros. Desde allí, puedes imprimir tu Certificado o añadirlo a tu perfil de LinkedIn. Si solo quieres leer y visualizar el contenido del curso, puedes auditar el curso sin costo.
Is financial aid available?
Sí, Coursera ofrece ayuda económica a los estudiantes que no pueden pagar la tarifa. Solicítala haciendo clic en el enlace de Ayuda económica que está debajo del botón “Inscribirse” a la izquierda. Se te pedirá que completes una solicitud. Recibirás una notificación en caso de que se apruebe. Deberás completar este paso para cada uno de los cursos que forman parte del Programa especializado, incluido el proyecto final. Obtén más información.
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.

¿Tienes más preguntas? Visita el Centro de Ayuda al Alumno.

Data Pipelines with TensorFlow Data Services