Chevron Left
Back to Build Better Generative Adversarial Networks (GANs)

Learner Reviews & Feedback for Build Better Generative Adversarial Networks (GANs) by DeepLearning.AI

4.7
stars
683 ratings

About the Course

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....

Top reviews

PK

Jan 25, 2021

I found that week 2 in this course is very abstract and non-technical thus I didn't like it. Week 1 and 3 were filled with relevant information and the final assignments were quite nice to accomplish.

MB

Aug 25, 2023

This course has helped me to dive deeper into the world of Generative AI through GANs and know what they can do and what are the advantages, benefits and disadvantages at the same time.

Filter by:

101 - 101 of 101 Reviews for Build Better Generative Adversarial Networks (GANs)

By Philip R K

•

Dec 12, 2025

Review: This course was a complete waste of time. Weeks 1–3 promised to teach “state‑of‑the‑art GANs” but delivered little more than hype, repetition, and links to external papers. Instead of actual instruction, the content was padded with congratulatory mimicry passages, optional labs, and “works cited” lists that simply redirected learners to arXiv papers, Medium blogs, or GitHub repos. Assignments demanded complex PyTorch implementations (StyleGAN, BigGAN, etc.), yet the lectures and notes provided no scaffolding or walkthroughs. The most advanced material was labeled “optional” and outsourced to dense research papers or gated blog posts, leaving learners unsupported. Even the acknowledgments list dozens of contributors, but the output is hollow — exposure without teaching. The result is credential theater: you’re told you’ve mastered GANs, but the course never actually teaches them. If you want to truly understand GAN architectures, you’ll need to study the original papers yourself. This specialization performs instruction rather than delivering it, and Weeks 1–3 prove that certification is prioritized over comprehension. Bottom line: Don’t waste your time. One star.