search

lipku / metahuman-stream

Real time interactive streaming digital human
https://livetalking-doc.readthedocs.io/
Apache License 2.0
3.46k stars 482 forks source link

在win 11 上启动项目 出现报错 #135

Open lmq886 opened 2 months ago

lmq886 commented 2 months ago

image

NeRFNetwork(
  (audio_net): AudioNet(
    (encoder_conv): Sequential(
      (0): Conv1d(44, 32, kernel_size=(3,), stride=(2,), padding=(1,))
      (1): LeakyReLU(negative_slope=0.02, inplace=True)
      (2): Conv1d(32, 32, kernel_size=(3,), stride=(2,), padding=(1,))
      (3): LeakyReLU(negative_slope=0.02, inplace=True)
      (4): Conv1d(32, 64, kernel_size=(3,), stride=(2,), padding=(1,))
      (5): LeakyReLU(negative_slope=0.02, inplace=True)
      (6): Conv1d(64, 64, kernel_size=(3,), stride=(2,), padding=(1,))
      (7): LeakyReLU(negative_slope=0.02, inplace=True)
    )
    (encoder_fc1): Sequential(
      (0): Linear(in_features=64, out_features=64, bias=True)
      (1): LeakyReLU(negative_slope=0.02, inplace=True)
      (2): Linear(in_features=64, out_features=32, bias=True)
    )
  )
  (audio_att_net): AudioAttNet(
    (attentionConvNet): Sequential(
      (0): Conv1d(32, 16, kernel_size=(3,), stride=(1,), padding=(1,))
      (1): LeakyReLU(negative_slope=0.02, inplace=True)
      (2): Conv1d(16, 8, kernel_size=(3,), stride=(1,), padding=(1,))
      (3): LeakyReLU(negative_slope=0.02, inplace=True)
      (4): Conv1d(8, 4, kernel_size=(3,), stride=(1,), padding=(1,))
      (5): LeakyReLU(negative_slope=0.02, inplace=True)
      (6): Conv1d(4, 2, kernel_size=(3,), stride=(1,), padding=(1,))
      (7): LeakyReLU(negative_slope=0.02, inplace=True)
      (8): Conv1d(2, 1, kernel_size=(3,), stride=(1,), padding=(1,))
      (9): LeakyReLU(negative_slope=0.02, inplace=True)
    )
    (attentionNet): Sequential(
      (0): Linear(in_features=8, out_features=8, bias=True)
      (1): Softmax(dim=1)
    )
  )
  (encoder_xy): GridEncoder: input_dim=2 num_levels=12 level_dim=1 resolution=64 -> 512 per_level_scale=1.2081 params=(163584, 1) gridtype=hash align_corners=False  
  (encoder_yz): GridEncoder: input_dim=2 num_levels=12 level_dim=1 resolution=64 -> 512 per_level_scale=1.2081 params=(163584, 1) gridtype=hash align_corners=False  
  (encoder_xz): GridEncoder: input_dim=2 num_levels=12 level_dim=1 resolution=64 -> 512 per_level_scale=1.2081 params=(163584, 1) gridtype=hash align_corners=False  
  (eye_att_net): MLP(
    (net): ModuleList(
      (0): Linear(in_features=36, out_features=16, bias=False)
      (1): Linear(in_features=16, out_features=1, bias=False)
    )
  )
  (sigma_net): MLP(
    (net): ModuleList(
      (0): Linear(in_features=69, out_features=64, bias=False)
      (1): Linear(in_features=64, out_features=64, bias=False)
      (2): Linear(in_features=64, out_features=65, bias=False)
    )
  )
  (encoder_dir): SHEncoder: input_dim=3 degree=4
  (color_net): MLP(
    (net): ModuleList(
      (0): Linear(in_features=84, out_features=64, bias=False)
      (1): Linear(in_features=64, out_features=3, bias=False)
    )
  )
  (unc_net): MLP(
    (net): ModuleList(
      (0): Linear(in_features=36, out_features=32, bias=False)
      (1): Linear(in_features=32, out_features=1, bias=False)
    )
  )
  (aud_ch_att_net): MLP(
    (net): ModuleList(
      (0): Linear(in_features=36, out_features=64, bias=False)
      (1): Linear(in_features=64, out_features=32, bias=False)
    )
  )
  (torso_deform_encoder): FreqEncoder: input_dim=2 degree=8 output_dim=34
  (anchor_encoder): FreqEncoder: input_dim=6 degree=3 output_dim=42
  (torso_deform_net): MLP(
    (net): ModuleList(
      (0): Linear(in_features=84, out_features=32, bias=False)
      (1): Linear(in_features=32, out_features=32, bias=False)
      (2): Linear(in_features=32, out_features=2, bias=False)
    )
  )
  (torso_encoder): GridEncoder: input_dim=2 num_levels=16 level_dim=2 resolution=16 -> 2048 per_level_scale=1.3819 params=(555520, 2) gridtype=tiled align_corners=False
  (torso_net): MLP(
    (net): ModuleList(
      (0): Linear(in_features=116, out_features=32, bias=False)
      (1): Linear(in_features=32, out_features=32, bias=False)
      (2): Linear(in_features=32, out_features=4, bias=False)
    )
  )
)
Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off]
D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torchvision\models\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead.
  warnings.warn(
D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torchvision\models\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' 
are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)
Traceback (most recent call last):
  File "E:\work\metahuman-stream-main\app.py", line 376, in <module>
    trainer = Trainer('ngp', opt, model, device=device, workspace=opt.workspace, criterion=criterion, fp16=opt.fp16,
  File "E:\work\metahuman-stream-main\ernerf\nerf_triplane\utils.py", line 655, in __init__
    self.criterion_lpips_alex = lpips.LPIPS(net='alex').to(self.device)
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\lpips\lpips.py", line 84, in __init__
    self.net = net_type(pretrained=not self.pnet_rand, requires_grad=self.pnet_tune)
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\lpips\pretrained_networks.py", line 59, in __init__
    alexnet_pretrained_features = tv.alexnet(pretrained=pretrained).features
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torchvision\models\_utils.py", line 142, in wrapper
    return fn(*args, **kwargs)
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torchvision\models\_utils.py", line 228, in inner_wrapper
    return builder(*args, **kwargs)
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torchvision\models\alexnet.py", line 114, in alexnet
    model.load_state_dict(weights.get_state_dict(progress=progress))
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torchvision\models\_api.py", line 63, in get_state_dict
    return load_state_dict_from_url(self.url, progress=progress)
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torch\hub.py", line 731, in load_state_dict_from_url
    return torch.load(cached_file, map_location=map_location)
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torch\serialization.py", line 705, in load
    with _open_zipfile_reader(opened_file) as opened_zipfile:
  File "D:\ProgramData\anaconda3\envs\nerfstream\lib\site-packages\torch\serialization.py", line 242, in __init__
    super(_open_zipfile_reader, self).__init__(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
Exception ignored in: <function Trainer.__del__ at 0x000001283CE60940>
Traceback (most recent call last):
  File "E:\work\metahuman-stream-main\ernerf\nerf_triplane\utils.py", line 708, in __del__
    if self.log_ptr:
AttributeError: 'Trainer' object has no attribute 'log_ptr'

这个怎么办啊？ 找不到问题

wx24736 commented 3 weeks ago

这个问题解决了吗?我也遇到这个问题了