Download Coursera – Generative Adversarial Networks (GANs) Specialization 2021-2

Description

Generative Adversarial Networks (GANs) Specialization, Training course Hostile reproductive networks (or GAN) is GANs are powerful machine learning models that are capable of producing realistic images, videos and sounds. Although these models from Game theory originated, but today have very wide applications, from improving cyber security and anonymizing data for privacy to producing artistic images, colorizing black and white images, increasing resolution, creating avatars, converting 2D photos to 3 Next and many others have. This course introduces you to the production of images by GANs and improves your level of knowledge from basic concepts to advanced techniques and is for software engineers, students and researchers in any field who are interested in machine learning and understanding the operation of GANs. are appropriate.

This course is divided into 3 sub-courses. In the first part, you will understand the fundamental parts of GANs, you will build a simple GAN using the PyTorch module, you will use convolutional layers to build advanced DCGANs that are able to process images and apply the W-Loss function, and You will learn how to build conditional GANs. The second part is dedicated to the challenges of evaluating GANs, and during it you will learn how to compare different GAN models, use the FID method to evaluate the accuracy and diversity of the model, identify sources of bias, and implement different techniques related to StyleGAN. The last part is dedicated to the practical use of GANs in data augmentation, privacy protection, making Pix2Pix and CycleGAN for image translation and other applications.

What you will learn:

• Understanding the components of GANs, building simple GANs with PyTorch and advanced DCGANs
• Comparison of manufacturer models, use of Fréchet Inception Distance – FID method, skew detection and implementation of StyleGAN techniques.
• Using GANs for data augmentation, privacy protection, mapping applications as well as testing and building Pix2Pix and CycleGAN for image translation.

What skills do you acquire:

• Generative Adversarial Networks – GANs
• Photo to photo generator and translator
• Controlled and conditional production
• WGANs, DCGANs and StyleGANs
• Bias in GANs
• And …

Specifications of Generative Adversarial Networks (GANs) Specialization:

• Publisher: Coursera
• teacher : Sharon Zhou, Eda Zhou, Eric Zelikman
• English language
• Education level: Intermediate
• Number: 3 courses
• Duration of the course: with a suggested time of 9 hours per week, approximately 3 months

courses

1. Build Basic Generative Adversarial Networks (GANs)
2. Build Better Generative Adversarial Networks (GANs)
3. Apply Generative Adversarial Networks (GANs)

prerequisites

• Learners should have a working knowledge of AI, deep learning, and convolutional neural networks. They should have intermediate Python skills as well as some experience with any deep learning framework (TensorFlow, Keras, or PyTorch). Learners should be proficient in basic calculus, linear algebra, and statistics.
• We highly recommend that you complete the Deep Learning Specialization prior to starting the GANs Specialization.

Pictures

Sample video

Installation guide

After extracting, watch with your favorite player.

English subtitle

Quality: 720p

download link

Download Coursera – Generative Adversarial Networks (GANs) Specialization 2021-2

Password file(s): www.downloadly.ir

Size

635 MB