TypeError: upfirdn2d() takes from 2 to 8 positional arguments but 10 were given

[picard314]

Dear Author,

I encountered this in running

python3 train.py --batch 3 --ckpt pretrained/tdmm_lizhen_full.pt --mode 3 path_to_dataset

I have installed stylegan_ops with logs looking fine.

I shall be most grateful if you may look into this. Thanks!

Sincerely,
Picard

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

logs in detail:

Traceback (most recent call last):
File "/mnt/swh/git/StyleAvatar/styleunet/train.py", line 340, in
train(args, loader, generator, discriminator, g_ema, g_optim, d_optim, device)
File "/mnt/swh/git/StyleAvatar/styleunet/train.py", line 147, in train
fake_img = generator(cond_img, latent)
File "/home/rtcai3/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/mnt/swh/git/StyleAvatar/styleunet/networks/generator.py", line 91, in forward
cond_img = self.dwt(condition_img)
File "/home/rtcai3/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/mnt/swh/git/StyleAvatar/styleunet/networks/modules.py", line 397, in forward
ll = upfirdn2d(input, self.ll, down=2)
File "/mnt/swh/git/StyleAvatar/styleunet/networks/stylegan2_ops/upfirdn2d.py", line 165, in upfirdn2d
out = UpFirDn2d.apply(input, kernel, up, down, pad)
File "/mnt/swh/git/StyleAvatar/styleunet/networks/stylegan2_ops/upfirdn2d.py", line 121, in forward
out = upfirdn2d_op.upfirdn2d(
TypeError: upfirdn2d() takes from 2 to 8 positional arguments but 10 were given

[LizhenWangT]

Please check the shape of cond_img, it should be (batch, 3, 256, 256)

[picard314]

Please check the shape of cond_img, it should be (batch, 3, 256, 256)

Thanks very much for your reply~ I've printed the shape of cond_img and it is "torch.Size([3, 3, 256, 256])". Any more information please~?

[LizhenWangT]

Any more information or someone else can reproduce this problem? I can not reproduce this bug, Orz. It seems you are using the geneface's env. Maybe there are some conflicts?

[picard314]

Thanks very much for your informations.

I just used your

from torch.utils.cpp_extension import load
module_path = os.path.dirname(file)
upfirdn2d_op = load(
"upfirdn2d",
sources=[
os.path.join(module_path, "upfirdn2d.cpp"),
os.path.join(module_path, "upfirdn2d_kernel.cu"),
],
)

instead of

import upfirdn2d as upfirdn2d_op

and it worked.

I use another env since my server does not support CUDA 11.7. But I guess env may be not the point. Could you please show me your ninja version? Mine is ninja 1.11.1. If compiled upfirdn2d does not have enough advantage on saving training time, I choose source code instead.

Cheers for your wonderful work~

Sincerely,
Picard