- 000
Hi, I hope your day is going well.
I would to ask whether or not it is possible to train a cGAN on MNIST using the StudioGAN framework. I have modified the code to allow for single-channel images and I'm using a pre-resizer to get the 28x28 images up to 32x32 so that I can feed them into present mod...
- 000
Could you help with this please? I'm trying to run a DCGAN model form the StudioGAN repo and using the checkpoint at Hugging face. No matter what I try it shows different error. Can any one please show me how to instantiate one of the GAN model like DCGAN, WGAN,... and then load a checkpoints and ju...
- 000
Hi MingKug and team,
Thanks for your great work in maintaining the repository. We just released our new work NoisyTwins [CVPR 2023], a regularizer for the latent space of GAN. The regularizer improves performance on GAN in terms of class consistency and diversity. As we implemented our work in Studi...
- 000
Hi & Good day!
In the section "4.3 Backbone networks for GAN evaluation" of your article, you have mentioned that you have used DINO as a metric. Does that mean you have used it (only) as a features extractor-- instead of extracting from the InceptionV3 network? Or you have performed some other...
- 000
Hi & good day!
Thanks for the paper, the repo and codes. I was searching through folders to find out the source code for image analysis, but didn't see anything relate to KNN, T-SNE, Frequency and semantic factorization. Where can I find them?
And is it possible to run any of analysis with just...
- 000
I know that all checkpoints are aviable at Hugging Face Hub, and to train a model we use -t falg like the following:
CUDA_VISIBLE_DEVICES=0 python3 src/main.py -t -metrics is fid prdc -cfg CONFIG_PATH -data DATA_PATH -save SAVE_PATH
But don'r know what's the falg for using weights that are saved...
- 000
Hi,
first of all I would like to thank you tremendously for your work. I'm certain that this repository alone has saved countless hours for researchers and developers all across the world.
I am conducting a series of experiments on image generation using ADCGAN and ReACGAN and I just noticed that, a...
- 000
set d_cond_mtd to "PD" in stylegan2, there is a bug: 'Discriminator' object has no attribute 'embedding'
- 000
Hi,
I'm conducting an experiment on MNIST datasets. I leave the config settings as default in config.py as follow:
`
# -----------------------------------------------------------------------------
# differentiable augmentation settings
# --------------------------------------------------...