Este curso forma parte de Programa especializado: TensorFlow: Data and Deployment

4.7
estrellas
384 calificaciones

Laurence Moroney

14.871 ya inscrito

ofrecido por

Programa especializado: TensorFlow: Data and Deploymentdeeplearning.ai

Acerca de este Curso

6809 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 final course, you’ll explore four different scenarios you’ll encounter when deploying models. You’ll be introduced to TensorFlow Serving, a technology that lets you do inference over the web. You’ll move on to TensorFlow Hub, a repository of models that you can use for transfer learning. Then you’ll use TensorBoard to evaluate and understand how your models work, as well as share your model metadata with others. Finally, you’ll explore federated learning and how you can retrain deployed models with user data while maintaining data privacy.

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.

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Certificado para compartir

Obtén un certificado al finalizar

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Curso 4 de 4 en

Programa Especializado - TensorFlow: Data and Deployment

Nivel intermedio

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

Aprox. 18 horas para completar

Inglés (English)

Subtítulos: Árabe (Arabic), Francés (French), Portugués (europeo), Italiano, Vietnamita, Alemán (German), Ruso (Russian), Inglés (English), Español (Spanish)

Qué aprenderás

Use TensorFlow Serving to do inference over the web

Navigate TensorFlow Hub, a repository of models that you can use for transfer learning

Evaluate how your models work and share model metadata using TensorBoard

Explore federated learning and how to retrain deployed models while maintaining data privacy

Habilidades que obtendrás

TensorFlow Serving
Machine Learning
federated learning
TensorFlow Hub
TensorBoard

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Certificado para compartir

Obtén un certificado al finalizar

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Curso 4 de 4 en

Programa Especializado - TensorFlow: Data and Deployment

Nivel intermedio

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

Aprox. 18 horas para completar

Inglés (English)

Subtítulos: Árabe (Arabic), Francés (French), Portugués (europeo), Italiano, Vietnamita, Alemán (German), Ruso (Russian), Inglés (English), Español (Spanish)

Instructor

Calificación del instructor

4,88/5 (35 calificaciones)

Laurence Moroney

Instructor

Lead AI Advocate, Google

344.721 alumnos

15 cursos

ofrecido por

deeplearning.ai

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

TensorFlow Extended

3 horas para completar

12 videos (Total 21 minutos), 5 lecturas, 3 cuestionarios

12 videos

Introduction, A conversation with Andrew Ng2m

Introduction24s

Serving3m

Installing TF Serving1m

TensorFlow Serving summary30s

Setup for serving2m

Serving1m

Predictions41s

Passing data to serving1m

Getting the predictions back1m

Running the colab2m

Complex model2m

5 lecturas

Downloading the Ungraded Labs and Programming Assignments10m

Installation link10m

TF server running in colab10m

Serving with Fashion MNIST10m

Ungraded Assignment - Serving with MNIST10m

1 ejercicio de práctica

Week 1 Quiz

Semana

Semana 2

6 horas para completar

Sharing pre-trained models with TensorFlow Hub

6 horas para completar

11 videos (Total 20 minutos), 7 lecturas, 3 cuestionarios

11 videos

Introduction, A conversation with Andrew Ng2m

Introduction to TF Hub2m

Transfer learning1m

Inference1m

Module storage2m

Text based models1m

Word embeddings1m

Experimenting with embeddings1m

Colab1m

Classify cats and dogs1m

Transfer learning1m

7 lecturas

Tensorflow Hub link10m

Link to saved models10m

Colab10m

Pre-trained Word Embeddings10m

Text Classification Colab10m

MobileNet model details10m

Colab10m

1 ejercicio de práctica

Week 2 Quiz

Semana

Semana 3

6 horas para completar

Tensorboard: tools for model training

6 horas para completar

10 videos (Total 16 minutos), 2 lecturas, 3 cuestionarios

Semana

Semana 4

2 horas para completar

Federated Learning

2 horas para completar

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

Reseñas

4.7

47 reseña

5 stars
81,02 %
4 stars
14,10 %
3 stars
3,33 %
2 stars
1,02 %
1 star
0,51 %

Principales reseñas sobre ADVANCED DEPLOYMENT SCENARIOS WITH TENSORFLOW

por DR6 de jun. de 2020

Enjoyed this specialization as much as I did the Tensorflow in practice. Thank you Laurence Moroney and Andrew Ng for getting these cool topics to all of us, so we can contribute back to community.

por FL19 de mar. de 2020

The first week is very useful. Tensorhub seems not helpful in a private company setting.\n\nI wish they talked about tf estimators which is also a common way to deploy models in SageMaker.

por SM10 de abr. de 2020

This topic seems to be very important but the content is not as good as rest of the weeks content, more explanations and more simple examples could have helped

por AS21 de ene. de 2021

The fact that there were still some problems in the Course regarding technical or exercise based, it shows that this material is relatively new in the domain.

Ver todas las reseñas

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. 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.

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.
¿Hay ayuda económica disponible?
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.

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

Advanced Deployment Scenarios with TensorFlow