Monthly Subscription Starting at AED 99 + VAT

Generative Deep Learning with TensorFlow
  • Level Professional
  • المدة 17 ساعات hours
  • الطبع بواسطة DeepLearning.AI
  • Offered by

عن

In this course, you will: a) Learn neural style transfer using transfer learning: extract the content of an image (eg. swan), and the style of a painting (eg. cubist or impressionist), and combine the content and style into a new image. b) Build simple AutoEncoders on the familiar MNIST dataset, and more complex deep and convolutional architectures on the Fashion MNIST dataset, understand the difference in results of the DNN and CNN AutoEncoder models, identify ways to de-noise noisy images, and build a CNN AutoEncoder using TensorFlow to output a clean image from a noisy one. c) Explore Variational AutoEncoders (VAEs) to generate entirely new data, and generate anime faces to compare them against reference images. d) Learn about GANs; their invention, properties, architecture, and how they vary from VAEs, understand the function of the generator and the discriminator within the model, the concept of 2 training phases and the role of introduced noise, and build your own GAN that can generate faces. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture, and gives them the tools to create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

الوحدات

Style Transfer Intro

    • 11 Videos
    • 5 Readings
    • 1 Lab
Show info about module content

1 Labs

  • Neural Style Transfer

11 Videos

  • Welcome to Course 4
  • Style Transfer Intro
  • Style Transfer Conceptual Overview
  • Pre-Processing Inputs
  • Extracting Style and Content Features
  • Total Loss and Content Loss
  • Style Loss
  • Update the Generated Image
  • Optional - Gram Matrix
  • Optional - Einstein Notation
  • Optional - Einsum in Code

5 Readings

  • Reference: A Neural Algorithm of Artistic Style
  • [IMPORTANT] Have questions, issues or ideas? Join our Forum!
  • Reference: Perceptual Losses for Real-Time Style Transfer and Super-Resolution
  • Reference: Visualizing and Understanding Convolutional Networks
  • Reference: numpy.einsum

Total Variation Loss

    • 1 Videos
    • 1 Lab
Show info about module content

1 Labs

  • Neural Style Transfer Part 2

1 Videos

  • Total Variation Loss

Fast Neural Style Transfer

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

1 Labs

  • Fast Neural Style Transfer

1 Videos

  • Fast Neural Style Transfer

1 Readings

  • Reference: Exploring the structure of a real-time, arbitrary neural artistic stylization network

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 1

Week 1 Quiz: Style Transfer

    • 1 Assignment
Show info about module content

1 Assignment

  • Style Transfer

Assignment: Style Transfer

    • 1 Programming
Show info about module content

1 Programming

  • Style Transfer Dog

What Are AutoEncoders?

    • 3 Videos
    • 2 Lab
Show info about module content

2 Labs

  • First Autoencoder
  • MNIST AutoEncoder

3 Videos

  • Introduction
  • First AutoEncoder
  • MNIST AutoEncoder

Deep AutoEncoders

    • 3 Videos
    • 3 Lab
Show info about module content

3 Labs

  • MNIST Deep AutoEncoder
  • Fashion MNIST - CNN AutoEncoder
  • Fashion MNIST - Noisy CNN AutoEncoder

3 Videos

  • MNIST Deep AutoEncoder
  • Convolutional AutoEncoder
  • Denoising with an AutoEncoder

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 2

Quiz Week 2: AutoEncoders

    • 1 Assignment
Show info about module content

1 Assignment

  • AutoEncoders

Assignment: AutoEncoder

    • 1 Programming
Show info about module content

1 Programming

  • AutoEncoder Model Loss and Accuracy

Variational AutoEncoders

    • 6 Videos
    • 2 Readings
    • 1 Lab
Show info about module content

1 Labs

  • MNIST Variational AutoEncoder

6 Videos

  • Variational AutoEncoders Overview
  • VAE Architecture and Code
  • Sampling Layer and Encoder
  • Decoder
  • Loss Function and Model Definition
  • Train the VAE Model

2 Readings

  • References: Kullback–Leibler divergence, Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders
  • Convolutional Variational AutoEncoders

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 3

Week 3 Quiz: Variational AutoEncoders

    • 1 Assignment
Show info about module content

1 Assignment

  • Variational AutoEncoders

Assignment: VAE Anime Faces

    • 1 Programming
Show info about module content

1 Programming

  • Anime Faces

What are GANs?

    • 3 Videos
    • 2 Readings
    • 1 Lab
Show info about module content

1 Labs

  • First GAN

3 Videos

  • Introduction
  • First GAN Architecture
  • First GAN Training Loop

2 Readings

  • Reference: GANs Specialization
  • Reference: Self-Normalizing Neural Networks

Deep GANs

    • 4 Videos
    • 2 Readings
    • 2 Lab
Show info about module content

2 Labs

  • First DCGAN
  • CelebA GAN Experiments

4 Videos

  • DCGANs
  • Face Generator
  • Face Generator Discriminator
  • Conclusions

2 Readings

  • Reference: - Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks ​, tf.keras.layers.LeakyReLU
  • Reference: Layer Normalization

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 4

Week 4 Quiz: GANs

    • 1 Assignment
Show info about module content

1 Assignment

  • GANs

End of Access to Lab Notebooks

    • 1 Readings
Show info about module content

1 Readings

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

Assignment: Generate Hands with GANs

    • 1 Programming
Show info about module content

1 Programming

  • Generated Hands

Course Resources

    • 2 Readings
Show info about module content

2 Readings

  • References
  • What next?

Acknowledgments

    • 2 Readings
Show info about module content

2 Readings

  • Acknowledgments
  • (Optional) Opportunity to Mentor Other Learners

Auto Summary

"Generative Deep Learning with TensorFlow" is a professional-level course designed for early and mid-career software and machine learning engineers. Taught by DeepLearning.AI on Coursera, it focuses on advanced TensorFlow features to build powerful ML models. Learners will explore neural style transfer, AutoEncoders, Variational AutoEncoders, and GANs, gaining hands-on experience with image processing and data generation. The course spans 1020 minutes and is available with a Starter subscription. Perfect for those with foundational TensorFlow knowledge looking to enhance their skills in data science and AI.

Laurence Moroney
Instructor

Laurence Moroney