search

zhengyuf / PointAvatar

Official Repository for CVPR 2023 paper PointAvatar: Deformable Point-based Head Avatars from Videos.
Other
318 stars 21 forks source link

ValueError: too many values to unpack (expected 2) #21

Closed saboorniazi closed 7 months ago

saboorniazi commented 9 months ago

shell command : scripts/exp_runner.py --conf ./confs/subject1.conf --is_eval Loading data ... Finish loading data ... creating the FLAME Decoder Canonical expression: tensor([[ 0.1662, 0.3928, 0.0172, 0.1365, -0.1178, 0.4555, -0.1693, -0.4088, 0.1085, 0.5834, -0.6895, -0.1363, -0.3936, 0.5161, -0.0302, -0.0410, -0.3208, -0.1618, 0.0507, 0.2476, -0.0370, -0.2849, 0.1857, -0.1914, -0.2390, 0.0215, 0.0572, 0.0187, -0.1371, -0.2072, -0.1512, -0.0693, 0.1041, -0.1097, 0.0102, -0.0312, 0.0773, -0.0876, -0.0166, 0.0174, -0.0392, 0.0148, -0.0696, 0.0560, -0.1038, -0.0079, -0.0469, 0.0922, 0.0014, 0.0480]]) /Users/saboor/anaconda3/envs/head/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") current point number: 400 current point number: 310718 Expression variance: None Optimizing test expressions Optimizing tracking, this is a slow process which is only used for calculating metrics. for qualitative animation, set optimize_expression and optimize_camera to False in the conf file. [0, 1, 2, 3, 4, 5, 6] /Users/saboor/anaconda3/envs/head/lib/python3.9/site-packages/torch/_functorch/deprecated.py:88: UserWarning: We've integrated functorch into PyTorch. As the final step of the integration, functorch.jacfwd is deprecated as of PyTorch 2.0 and will be deleted in a future version of PyTorch >= 2.3. Please use torch.func.jacfwd instead; see the PyTorch 2.0 release notes and/or the torch.func migration guide for more details https://pytorch.org/docs/master/func.migrating.html warn_deprecated('jacfwd') /Users/saboor/anaconda3/envs/head/lib/python3.9/site-packages/torch/_functorch/deprecated.py:61: UserWarning: We've integrated functorch into PyTorch. As the final step of the integration, functorch.vmap is deprecated as of PyTorch 2.0 and will be deleted in a future version of PyTorch >= 2.3. Please use torch.vmap instead; see the PyTorch 2.0 release notes and/or the torch.func migration guide for more details https://pytorch.org/docs/master/func.migrating.html warn_deprecated('vmap', 'torch.vmap') Traceback (most recent call last): File "/Users/saboor/Documents/PointAvatar/code/scripts/exp_runner.py", line 51, in runner.run() File "/Users/saboor/Documents/PointAvatar/code/../code/scripts/test.py", line 176, in run model_outputs = self.model(model_input) File "/Users/saboor/anaconda3/envs/head/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/Users/saboor/anaconda3/envs/head/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, **kwargs) File "/Users/saboor/Documents/PointAvatar/code/../code/model/point_avatar_model.py", line 177, in forward images = self._render(transformed_point_cloud, cameras) File "/Users/saboor/Documents/PointAvatar/code/../code/model/point_avatar_model.py", line 96, in _render images, weights = self.compositor( ValueError: too many values to unpack (expected 2)

zhengyuf commented 8 months ago

Hi,

we use a slightly modified version of Pytorch3D. You can follow the instructions in our README to install it.