StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
My system is linux, and when I use main.py, it calls config.py. When “import utils.misc as misc“ and so on, it will report an error. However, if you add an empty init.py under src/utils, there will be no error.
Hi,
I discovered that, in WGAN-GP for CIFAR10, Discriminator and Generator loss always display NaN (Not A Number) after some time elapsed.
The problem existed when I ran src/configs/CIFAR10/WGAN-GP.yaml file but I did not check if this also happens in other training data.
+) The one thing I conside...
In the current version of master branch(which is the only branch), config files for running experiments on Tiny ImageNet dataset don't exist. I remember that the configs were previously defined in src/configs/Tiny_ImageNet folder.
I noticed that the folder was removed with the commit on July 3, 2022...
Hi, I am testing DDP code with 4 V100 GPU as below,
export MASTER_ADDR="localhost"
export MASTER_PORT=2222
CUDA_VISIBLE_DEVICES=0,1,2,3 python3 src/main.py -t -metrics none -cfg CONFIG_PATH -data DATA_PATH -save SAVE_PATH -DDP -sync_bn -mpc
but im having less than 48% gpu utilization.
Could I get so...
Hi,
I fail to load the pretrain weight located "Pre-trained_weights/CIFAR10/BigGAN-Deep-train-2020_09_17_13_44_46". I tried with both "src/configs/CIFAR10/BigGAN-Deep-StudioGAN.yaml" and "src/configs/CIFAR10/BigGAN-Deep.yaml". Neither of them seem to work.
And the folder "Pre-trained_weights/CIFAR10...
Hi, I'm trying to train StyleGAN2-D2DCE-ADA.yaml . All of a sudden it got stuck at this step: 'Setting up PyTorch plugin "bias_act_plugin"', as you can see in the screenshot:
I left for almost an hour and it was stuck there. Any ideas why this might happen?
This is the command I'm using to train:...
Hi all, could you please let me know what is the command to generate images with the trained models? I trained several approaches, but none of them work. I always face the issue: