************ Create mesh Render Transformer Model ************
Load Pre-trained CNN Encoder weights of ROME ...
==> Add Sine PositionEmbedding~
PolyMeshT::add_face: complex edge
PolyMeshT::add_face: complex edge
/home/sixy/CVTHead-main/models/spiralnet.py:20: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at /opt/conda/conda-bld/pytorch_1678402374358/work/torch/csrc/utils/tensor_new.cpp:245.)
torch.LongTensor([spmat.tocoo().row,
Traceback (most recent call last):
File "/home/sixy/CVTHead-main/inference.py", line 215, in
main(args)
File "/home/sixy/CVTHead-main/inference.py", line 196, in main
ckpt = torch.load(args.ckpt_pth, map_location="cpu")["model"]
File "/home/sixy/miniconda3/envs/cvthead/lib/python3.9/site-packages/torch/serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/home/sixy/miniconda3/envs/cvthead/lib/python3.9/site-packages/torch/serialization.py", line 1018, in _legacy_load
return legacy_load(f)
File "/home/sixy/miniconda3/envs/cvthead/lib/python3.9/site-packages/torch/serialization.py", line 904, in legacy_load
tar.extract('storages', path=tmpdir)
File "/home/sixy/miniconda3/envs/cvthead/lib/python3.9/tarfile.py", line 2281, in extract
tarinfo = self._get_extract_tarinfo(member, filter_function, path)
File "/home/sixy/miniconda3/envs/cvthead/lib/python3.9/tarfile.py", line 2288, in _get_extract_tarinfo
tarinfo = self.getmember(member)
File "/home/sixy/miniconda3/envs/cvthead/lib/python3.9/tarfile.py", line 1971, in getmember
raise KeyError("filename %r not found" % name)
KeyError: "filename 'storages' not found"
HowieMa
