Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Using MAGE for image generation in my code #42

Open
itayreznik opened this issue Dec 1, 2024 · 0 comments
Open

Using MAGE for image generation in my code #42

itayreznik opened this issue Dec 1, 2024 · 0 comments

Comments

@itayreznik
Copy link

Hi,
I need to use one of the generators that appear in this repo for my research's code, let's say I need to use MAGE.
I am a new master's student in the field of machine learning.
I have an optimization algorithm that allows generating images that are controversial (that look like 2 classes to a human). I do that with a GAN I imported from some repo and 2 robust classifiers trained adversarially on Imagenet.
I do that by "training" the GAN's input vector's entries - optimizing the input vectors in each iteration. The loss function for this optimization contains one classifier's output probability for dog and the other classifier's output probability for cat (lets say). I want to maximize both of these probabilities.
I use the GAN just for purely generating the image in each iteration of the algorithm. It works well, the probabilities are both high as wanted, but the images are still not good and expressive enough to give them to actual humans for classification.
I need to use one of your generators in the same way. No training of MAGE needed, not anything. I purely need to import it and use it for generating images.
Unfortunately I'm not experienced enough and I can't seem to understand how to get to a point where I use your generator. I read the README file multiple times.
Could someone please instruct me with what I have to do?

Thanks a lot

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant