search

davidbau / rewriting

Rewriting a Deep Generative Model, ECCV 2020 (oral). Interactive tool to directly edit the rules of a GAN to synthesize scenes with objects added, removed, or altered. Change StyleGANv2 to make extravagant eyebrows, or horses wearing hats.
https://rewriting.csail.mit.edu/
MIT License
537 stars 76 forks source link

Rendering in isolation from neighbouring features #9

Closed vidit98 closed 3 years ago

vidit98 commented 3 years ago

Hi, I found the idea of seeing weights as associative memory very interesting. Could you please explain in some more detail what do you mean by rendering feature patch in isolation from neighboring features?

For example, if a network generates an output of 256x256 and I want to generate an isolated patch of 32x32. If we are analyzing a layer L with feature maps with spatial size 32x32, should the features excluding a 4x4 patch be set to 0 and so on for other layers to get final output?

davidbau commented 3 years ago

That is exactly right.

On Sun, Mar 28, 2021 at 11:59 AM Vidit @.***> wrote:

Hi, I found the idea of seeing weights as associative memory very interesting. Could you please explain in some more detail what do you mean by rendering feature patch in isolation from neighboring features?

For example, if a network generates an output of 256x256 and I want to generate an isolated patch of 32x32. If we are analyzing a layer L with feature maps with spatial size 32x32, should the features excluding a 4x4 patch be set to 0 and so on for other layers to get final output?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/davidbau/rewriting/issues/9, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA2MN2DF6N4LFVE25PDG5YLTF5G6JANCNFSM4Z6FJUNA .