search

boycehbz / DMMR

The code for 3DV 2021 paper "Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras"
MIT License
78 stars 6 forks source link

RuntimeError: einsum(): subscript l has size 300 for operand 1 which does not broadcast with previously seen size 10 #20

Open zmhsmart opened 3 months ago

zmhsmart commented 3 months ago

/home/pbc/miniconda3/envs/zxh/lib/python3.8/site-packages/torch/utils/_contextlib.py:125: UserWarning: Decorating classes is deprecated and will be disabled in future versions. You should only decorate functions or methods. To preserve the current behavior of class decoration, you can directly decorate the init method and nothing else. warnings.warn("Decorating classes is deprecated and will be disabled in " Processing: doubleB/Camera00/00001.jpg load pretrain parameters from data/motionprior_hp.pkl /home/pbc/miniconda3/envs/zxh/lib/python3.8/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( /home/pbc/miniconda3/envs/zxh/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=ResNet50_Weights.IMAGENET1K_V1. You can also use weights=ResNet50_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg) betas shape: torch.Size([1, 10]) shape_disps shape: torch.Size([6890, 3, 300]) Traceback (most recent call last): File "main.py", line 56, in main(args) File "main.py", line 33, in main setting = load_camera(data, setting, args) File "/home/pbc/project/inference/DMMR/DMMR-main/core/utils/module_utils.py", line 694, in load_camera extris = extris_est(spin, data, data_folder, intris) File "/home/pbc/project/inference/DMMR/DMMR-main/core/utils/module_utils.py", line 568, in extris_est output, vert = spin(norm_img) File "/home/pbc/miniconda3/envs/zxh/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "/home/pbc/project/inference/DMMR/DMMR-main/core/SPIN/spin.py", line 33, in forward pred_output, verts = self.smpl(betas=pred_betas, body_pose=pred_rotmat[:,1:], global_orient=pred_rotmat[:,0].unsqueeze(1), pose2rot=False) File "/home/pbc/miniconda3/envs/zxh/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "/home/pbc/project/inference/DMMR/DMMR-main/core/SPIN/smpl.py", line 19, in forward smpl_output = super(SMPL, self).forward(args, kwargs) File "/home/pbc/project/inference/DMMR/DMMR-main/core/smplx/body_models.py", line 373, in forward vertices, joints = lbs(betas, full_pose, self.vtemplate, File "/home/pbc/project/inference/DMMR/DMMR-main/core/smplx/lbs.py", line 179, in lbs v_shaped = v_template + blendshapes(betas, shapedirs) File "/home/pbc/project/inference/DMMR/DMMR-main/core/smplx/lbs.py", line 268, in blend_shapes blend_shape = torch.einsum('bl,mkl->bmk', [betas, shape_disps]) File "/home/pbc/miniconda3/envs/zxh/lib/python3.8/site-packages/torch/functional.py", line 373, in einsum return einsum(equation, *_operands) File "/home/pbc/miniconda3/envs/zxh/lib/python3.8/site-packages/torch/functional.py", line 378, in einsum return _VF.einsum(equation, operands) # type: ignore[attr-defined] RuntimeError: einsum(): subscript l has size 300 for operand 1 which does not broadcast with previously seen size 10

![Uploading PixPin_2024-07-16_20-41-50.png…]()

I am glad to see this exciting project, but I got this error when running it. My smpl model name is correct, but the dimension is wrong. How should I solve it? Thank you?

boycehbz commented 3 months ago

Please confirm that your SMPL_NEUTRAL.pkl is downloaded from SMPLify website. Thank you!

zmhsmart commented 2 months ago

Thanks, I have successfully run the code!!!