You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The text was updated successfully, but these errors were encountered:
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
The text was updated successfully, but these errors were encountered: