PyTorch-StudioGAN icon indicating copy to clipboard operation
PyTorch-StudioGAN copied to clipboard

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Results 42 PyTorch-StudioGAN issues
Sort by recently updated
recently updated
newest added

During the Evaluation phase (evaluate fid prdc of the model) when I train the model, sometimes it takes ten minutes, sometimes two or three hours. And the gpu utilization is...

How can I resume the GAN I have been training, if I canceled the training, using the weights being saved in the checkpoints folder? Thanks

Hi CUDA_VISIBLE_DEVICES=O python src/main.py -t -hdf5 -l -batch_stat -metrics is fid prdc -ref "test" -best --project Cifar10-wgangp -cfg src/configs/CIFAR10/WGAN-GP.yaml -ckpt author_trained_models/cifar10/wgangp/WGAN-GP-train-2020_09_16_14_17_00 -data cifar10 -save results I suffer from issue: RuntimeError:...

For example, when I try to execute FA I get this error ``` [INFO] 2022-04-04 05:47:59 > Run frequency analysis (use 8 fake and valid images). Traceback (most recent call...

Hi, your work is very interesiting I do a [simple test on mnist](https://www.kaggle.com/code/tom99763/similarity-based-classifier?scriptVersionId=91987582) I think this loss has potential to extend to hard recognition task, do you plain to do...

Hi, I'm training ReACGAN with train dataset size being: 28003, img_size:128, and 4 gpus. It takes 10 hours for 10% of training to be done. Are there any configurations that...

Hi! This project is very nice. I saw that at the moment you're sharing the model weights via Google Drive links, but I think it would be very nice if...

Dear Authors, Thank you for your great work. We are happy to share with you that our paper [A Unified View of cGANs with and without Classifiers](https://arxiv.org/abs/2111.01035) is accepted by...

Excuse me, it seems that the google drive does not contain the checkpoint for StyleGAN on FQ dataset? How can I find it.

ACGAN causes TypeError ``` TypeError: forward() got an unexpected keyword argument 'h' ``` This PR avoid the error.