DeepLearning.AI - Generative Deep Learning with TensorFlow
- Offered byCoursera
Generative Deep Learning with TensorFlow at Coursera Overview
Duration | 22 hours |
Start from | Start Now |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Intermediate |
Official Website | Explore Free Course  |
Credential | Certificate |
Generative Deep Learning with TensorFlow at Coursera Highlights
- Shareable Certificate Earn a Certificate upon completion
- 100% online Start instantly and learn at your own schedule.
- Course 4 of 4 in the TensorFlow: Advanced Techniques Specialization
- Flexible deadlines Reset deadlines in accordance to your schedule.
- Intermediate Level Python, TensorFlow, and deep learning TensorFlow's Functional API and Gradient Tape (covered in course 1 and 2 of this specialization)
- Approx. 22 hours to complete
- English Subtitles: English
Generative Deep Learning with TensorFlow at Coursera Course details
- 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.
Generative Deep Learning with TensorFlow at Coursera Curriculum
Week 1: Style Transfer
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
Total Variation Loss
Fast Neural Style Transfer
Connect with your mentors and fellow learners on Slack!
Reference: A Neural Algorithm of Artistic Style
Reference: Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Reference: Visualizing and Understanding Convolutional Networks
Reference: numpy.einsum
Reference: Exploring the structure of a real-time, arbitrary neural artistic stylization network
Style Transfer
Week 2: AutoEncoders
Introduction
First AutoEncoder
MNIST AutoEncoder
MNIST Deep AutoEncoder
Convolutional AutoEncoder
Denoising with an AutoEncoder
AutoEncoders
Week 3: Variational AutoEncoders
Variational AutoEncoders Overview
VAE Architecture and Code
Sampling Layer and Encoder
Decoder
Loss Function and Model Definition
Train the VAE Model
References: Kullback?Leibler divergence, Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders
Convolutional Variational AutoEncoders
Variational AutoEncoders
Week 4: GANs
Introduction
First GAN Architecture
First GAN Training Loop
DCGANs
Face Generator
Face Generator Discriminator
Conclusions
Reference: GANs Specialization
Reference: Self-Normalizing Neural Networks
Reference: - Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks ?, tf.keras.layers.LeakyReLU
Reference: Layer Normalization
References
What next?
Acknowledgments
GANs
Generative Deep Learning with TensorFlow at Coursera Admission Process
Important Dates
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?