Error Running Demo

[AlexKashi]

After following the installation instructions, I get the following error running Cuda 11.6 on an RTX 2080ti

Traceback (most recent call last):
  File "/home/alex/Spring-2022/CV/GAN/resources/stylegan_xl/train.py", line 332, in <module>
    main()  # pylint: disable=no-value-for-parameter
  File "/home/alex/miniconda3/envs/sgxl/lib/python3.9/site-packages/click/core.py", line 1128, in __call__
    return self.main(*args, **kwargs)
  File "/home/alex/miniconda3/envs/sgxl/lib/python3.9/site-packages/click/core.py", line 1053, in main
    rv = self.invoke(ctx)
  File "/home/alex/miniconda3/envs/sgxl/lib/python3.9/site-packages/click/core.py", line 1395, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/alex/miniconda3/envs/sgxl/lib/python3.9/site-packages/click/core.py", line 754, in invoke
    return __callback(*args, **kwargs)
  File "/home/alex/Spring-2022/CV/GAN/resources/stylegan_xl/train.py", line 317, in main
    launch_training(c=c, desc=desc, outdir=opts.outdir, dry_run=opts.dry_run)
  File "/home/alex/Spring-2022/CV/DogeGAN/resources/stylegan_xl/train.py", line 104, in launch_training
    subprocess_fn(rank=0, c=c, temp_dir=temp_dir)
  File "/home/alex/Spring-2022/CV/GAN/resources/stylegan_xl/train.py", line 49, in subprocess_fn
    training_loop.training_loop(rank=rank, **c)
  File "/home/alex/Spring-2022/CV/GAN/resources/stylegan_xl/training/training_loop.py", line 339, in training_loop
    loss.accumulate_gradients(phase=phase.name, real_img=real_img, real_c=real_c, gen_z=gen_z, gen_c=gen_c, gain=phase.interval, cur_nimg=cur_nimg)
  File "/home/alex/Spring-2022/CV/GAN/resources/stylegan_xl/training/loss.py", line 121, in accumulate_gradients
    loss_Gmain.backward()
  File "/home/alex/miniconda3/envs/sgxl/lib/python3.9/site-packages/torch/_tensor.py", line 363, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
  File "/home/alex/miniconda3/envs/sgxl/lib/python3.9/site-packages/torch/autograd/__init__.py", line 173, in backward
    Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
  File "/home/alex/miniconda3/envs/sgxl/lib/python3.9/site-packages/torch/autograd/function.py", line 253, in apply
    return user_fn(self, *args)
  File "/home/alex/Spring-2022/CV/GAN/resources/stylegan_xl/torch_utils/ops/conv2d_gradfix.py", line 144, in backward
    grad_weight = Conv2dGradWeight.apply(grad_output, input)
  File "/home/alex/Spring-2022/CV/GAN/resources/stylegan_xl/torch_utils/ops/conv2d_gradfix.py", line 173, in forward
    return torch._C._jit_get_operation(name)(weight_shape, grad_output, input, padding, stride, dilation, groups, *flags)
RuntimeError: No such operator aten::cudnn_convolution_transpose_backward_weight

[xl-sr]

seems like an issue with your cuda-toolkit + pytorch. You could try downgrading to cuda 11.3.

[AlexKashi]

Downgraded to 11.3

nvidia-smi
Driver Version: 465.31 CUDA Version: 11.3
nvcc -V
release 11.3, V11.3.58

I still get the error when running:

python train.py --outdir=./training-runs/pokemon --cfg=stylegan3-t --data=./data/pokemon64.zip --gpus=1 --batch=1 --mirror=1 --snap 10 --batch-gpu 1 --kimg 10000 --syn_layers 10

[xl-sr]

do you get the same error when running the StyleGAN3 repo?

[chae-won-kim]

Try removing the $HOME/.cache/torch_extensions folder and running the training code again.

I encountered the same error when my PyTorch version was 1.8. I updated my PyTorch version from 1.8 to 1.10, then tried running the training code, but still had the same issue. Once I removed $HOME/.cache/torch_extensions and re-ran the code, I was able to solve the error.

[ghost]

Hi there when do they release the large model?

[xl-sr]

@chae-won-kim thanks for the tip, will add it to the README :)

@19Ply3 I just added the ImageNet512 and FFHQ512 models, the megapixel models will be added soon, see README.

[Youzebin]

HELLO, when i removed $HOME/.cache/torch_extensions and re ran the code, i still had the saem issue, do you know why??

[Youzebin]

when i re ran the code, $HOME/.cache/torch_extensions will appear again. so i think this can not solve the problem.

[Youzebin]

HELLO, when i removed $HOME/.cache/torch_extensions and re ran the code, i still had the saem issue, do you know why??

same

[woctezuma]

I think you need to downgrade CUDA as well.

[Youzebin]

I think you need to downgrade CUDA as well
I downgraded cuda to 11.3, and re ran the code. but this problem can not be solved

[Youzebin]

I think you need to downgrade CUDA as well.

can you train the model now? if you can, did you meet the same question as me??

[chae-won-kim]

@Youzebin
It would be really helpful if you shared your environment settings :/
Also, try referring to the stylegan3 troubleshooting page to set up your environment.

[Youzebin]

nvidia-smi
Driver Version: 470.82.00 CUDA Version: 11.4
nvcc -V
release 11.3, V11.3.58
pytorch1.11.0 cu113
python3.9

thank you

[chae-won-kim]

nvidia-smi
Driver Version: 470.82.00 CUDA Version: 11.4
nvcc -V
release 11.3, V11.3.58
pytorch1.11.0 cu113
python3.9

What about your gcc version?

[Youzebin]

9.3.0

[ghost]

Hi xl-sr does stylegan xl large model allows you to use your own pictures?

[Youzebin]

您好 xl-sr stylegan xl large model 是否允许您使用自己的图片？
yes.
Hello, it is possible to use your own pictures, but if your pictures are conditional dataset, you need to add some functions to dataset_tool.py, if they are unconditional dataset, you can prepare the data according to the readme, the pokemon in the readme is a folder of pictures, I think your own pictures are also A folder

[Youzebin]

In the meantime, this issue is closed, if you want to ask other questions, you can create a new issue