skhu101
commented
7 months ago Hi, thanks for your interest in our work. Do you spot any errors if you directly run our code? If you can successfully run our code, one quick idea is to compare the differences, e.g., grid size and number.
I use the point-level feature on SMPL vertices,and Here is the detailed error: File "/home/yejr/Digital_Avater/GauHuman-my-version/scene/gaussian_model.py", line 955, in coarse_deform_c2source point_feature = self.encoder_3d(canonical_sp_conv_volume, grid_coords) # torch.Size([b, 390, 102464]) File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "/home/yejr/Digital_Avater/GauHuman-my-version/sherf_nets/utils.py", line 168, in forward net = self.down0(net) File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/spconv/pytorch/modules.py", line 138, in forward input = module(input) File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/spconv/pytorch/conv.py", line 741, in forward return self._conv_forward(self.training, input, self.weight, self.bias, add_input, File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/spconv/pytorch/conv.py", line 415, in _conv_forward raise e File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/spconv/pytorch/conv.py", line 392, in _conv_forward res = ops.get_indice_pairs_implicit_gemm( File "/media/data4/yejr/conda_env/gauhuman/lib/python3.8/site-packages/spconv/pytorch/ops.py", line 642, in get_indice_pairs_implicit_gemm raise ValueError(msg) ValueError: Your points vanished here, this usually because you provide conv params that may ignore some input points. Example: spatial_shape=[8, 200, 200] ksize=3 stride=2 padding=[0, 1, 1] dilation=1 Coordinates=[[0, 7, 153, 142]] these params will cause ALL points in z == 7 dropped because of padding_z=0. enlarge your spatial shape or change your conv param to make sure every input point has a corresponding output point. Your Conv Params: spatial_shape=[96, 320, 384] ksize=[3, 3, 3] stride=[2, 2, 2] padding=[1, 1, 1] dilation=[1, 1, 1] How should I do?