Chevron Left
Build Better Generative Adversarial Networks (GANs) に戻る

deeplearning.ai による Build Better Generative Adversarial Networks (GANs) の受講者のレビューおよびフィードバック

4.7
539件の評価
83件のレビュー

コースについて

In this course, you will: - Assess the challenges of evaluating GANs and compare different generative models - Use the Fréchet Inception Distance (FID) method to evaluate the fidelity and diversity of GANs - Identify sources of bias and the ways to detect it in GANs - Learn and implement the techniques associated with the state-of-the-art StyleGANs The DeepLearning.AI Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach. It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more. Build a comprehensive knowledge base and gain hands-on experience in GANs. Train your own model using PyTorch, use it to create images, and evaluate a variety of advanced GANs. This Specialization provides an accessible pathway for all levels of learners looking to break into the GANs space or apply GANs to their own projects, even without prior familiarity with advanced math and machine learning research....

人気のレビュー

GJ

2020年9月30日

Very good course! Helpful to understand evaluation metrics and details of Style GAN. It was also super cool to have the bias section that is not as well known as the others. Loved it!

AB

2021年3月24日

Great material...but the stylegan code implementation requires more video material. Instead adding one more week for ProGan part before stylegan would be helpful for the learners.

フィルター:

Build Better Generative Adversarial Networks (GANs): 76 - 81 / 81 レビュー

by Karan S

2022年5月16日

Too fast speaking, some mathematical concepts difficult to clear

by Michael K

2020年11月6日

too easy

by Shounak D

2022年7月31日

The second course was easily the low point of the curriculum. At the end, I wasnt fully able to implement Style GANs, the thing which this course sets off to do. This led to frustration and didnt feel like anything was accomplished compared to Course 1 and Course 3 where we were able to implement the whole GAN architecture. The argument: 'We have left that as assignment for students' OR 'based on the information, the students can implement the GAN' is flawed because If we students were that smart and good at it, we would have just read the papers, or watched YouTube video and implemented the paper ourselves. We wouldnt have bought a course then. But apart from that, Course 1 and Course 3 were pretty decent. We felt like we accomplished something and learnt new.

by Daniil K

2021年8月28日

T​he material is great; however, after the completion you lose the access to assignments and the only way to restore it is to subscribe again.

by Злобин Я Н

2021年8月8日

This course will have a minimum of mathematics explaining the work of GAN

by Bedrich P

2021年8月21日

I want to learn GANs not "fairness in ML"