mingtaoguo / draggan_pytorch Goto Github PK

I have a problem and report an error:bias_act.cu ninja: build stopped: subcommand failed.
How do I solve this?

The error message:
AttributeError: 'DragGAN' object has no attribute 'tar_points'

How can I get high quality image after init. The image I upload is good enough. It is a beatiful woman image.

The image after Init is

PS D:\DragGAN_pytorch-main> python draggan_stylegan2_human.py
Traceback (most recent call last):
File "D:\DragGAN_pytorch-main\draggan_stylegan2_human.py", line 165, in
draggan = DragGAN("stylegan2-human-1024x1024.pt", device="cuda")
File "D:\DragGAN_pytorch-main\draggan_stylegan2_human.py", line 101, in init
self.G.load_state_dict(torch.load(ckpt))
with _open_file_like(f, 'rb') as opened_file:
File "d:\anaconda3\lib\site-packages\torch\serialization.py", line 321, in _open_file_like
return _open_file(name_or_buffer, mode)
File "d:\anaconda3\lib\site-packages\torch\serialization.py", line 302, in init
super().init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'stylegan2-human-1024x1024.pt'
PS D:\DragGAN_pytorch-main> python draggan_stylegan2_human.py
Setting up PyTorch plugin "bias_act_plugin"... Failed!
Traceback (most recent call last):
File "D:\DragGAN_pytorch-main\draggan_stylegan2_human.py", line 166, in
init_img = draggan.gen_image(seed=seed)
File "D:\DragGAN_pytorch-main\draggan_stylegan2_human.py", line 107, in gen_image
latent = self.G.mapping(z, label, truncation_psi=1.0, truncation_cutoff=None)
File "d:\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1502, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "d:\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1511, in _call_impl
return forward_call(*args, **kwargs)
File "D:\DragGAN_pytorch-main\training\networks_stylegan2_human.py", line 231, in forward
x = layer(x)
File "d:\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1502, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "d:\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1511, in _call_impl
return forward_call(*args, **kwargs)
File "D:\DragGAN_pytorch-main\training\networks_stylegan2_human.py", line 119, in forward
x = bias_act.bias_act(x, b, act=self.activation)
File "D:\DragGAN_pytorch-main\torch_utils\ops\bias_act.py", line 84, in bias_act
if impl == 'cuda' and x.device.type == 'cuda' and _init():
File "D:\DragGAN_pytorch-main\torch_utils\ops\bias_act.py", line 41, in _init
_plugin = custom_ops.get_plugin(
File "D:\DragGAN_pytorch-main\torch_utils\custom_ops.py", line 84, in get_plugin
raise RuntimeError(f'Could not find MSVC/GCC/CLANG installation on this computer. Check _find_compiler_bindir() in "{file}".')
RuntimeError: Could not find MSVC/GCC/CLANG installation on this computer. Check find_compiler_bindir() in "D:\DragGAN_pytorch-main\torch_utils\custom
ops.py".

机器学习小白一名，跑大神的包出了各种错，建了个学友们的交流学习互助群，答疑解惑交流提高，欢迎各位大神加入

I hope write can make it as soon as possilble

An error occurred when I tried this project for removing the watermark I added to the test image(a visible one, not the invisible one I referred to below). The snapshot of the Hugging Face website of this project is shown below.

(I covered the original image since there might be an invisible watermark containing my personal information on it.)
I'm not sure whether it is the fault of the project itself, the Internet or my PC. I just read the note on the website and decided to leave the issue here. I have only extremely poor knowledge of AI and my English is poor, too. If I had done something wrong and caused you trouble or wasted your time, I'm terribly sorry.
I sincerely hope your project will be better and better.