Lesson 12: Deep Learning Part 2 2018 - Generative Adversarial Networks (GANs)

We start today with a deep dive into the DarkNet architecture used in YOLOv3, and use it to better understand all the details and choices that you can make when implementing a resnet-ish architecture. The basic approach discussed here is what we used to win the DAWNBench competition!

Then we’ll learn about Generative Adversarial Networks (GANs). This is, at its heart, a different kind of loss function. GANs have a generator and a discriminator that battle it out, and in the process combine to create a generative model that can create highly realistic outputs. We’ll be looking at the Wasserstein GAN variant, since it’s easier to train and more resilient to a range of hyperparameters.

[parthrawri]

Omg, I just stepped on a gold mine. You sir are the best. Thank you for these videos! @JeremyHoward

[thevivekmathema]

can you publish the code yo used to demonstrate the GANs

[shivenkhajuria]

Page not found.Kindly guide on this!!!

[lambertwolterbeekmuller]

this series is great and I don’t want to sound ungrateful, but can we have a edited version with some of the more disruptive questions moved to very end?

[MrChristian]

what does the "ni" mean in the self.conv1=conv_layer function mean??

[MrChristian]

I need information for my GAN to come up with a medicine therapeutic. Where can I go to get sample data for training??

[MrChristian]

I get an error message: ModuleNotFoundError: No module named 'fastai'. What library do I have to install or import??