You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I installed point-e using pip install -e . within a conda virtual environment (Ubuntu 22.10). I am able to run the other two jupyter notebooks, but get the following error in txt2pointcloud:
File ~/.local/lib/python3.10/site-packages/torch/serialization.py:797, in load(f, map_location, pickle_module, weights_only, **pickle_load_args)
792 if _is_zipfile(opened_file):
793 # The zipfile reader is going to advance the current file position.
794 # If we want to actually tail call to torch.jit.load, we need to
795 # reset back to the original position.
796 orig_position = opened_file.tell()
--> 797 with _open_zipfile_reader(opened_file) as opened_zipfile:
798 if _is_torchscript_zip(opened_zipfile):
799 warnings.warn("'torch.load' received a zip file that looks like a TorchScript archive"
800 " dispatching to 'torch.jit.load' (call 'torch.jit.load' directly to"
801 " silence this warning)", UserWarning)
I installed point-e using pip install -e . within a conda virtual environment (Ubuntu 22.10). I am able to run the other two jupyter notebooks, but get the following error in txt2pointcloud:
untimeError Traceback (most recent call last)
Cell In[2], line 15
12 upsampler_diffusion = diffusion_from_config(DIFFUSION_CONFIGS['upsample'])
14 print('downloading base checkpoint...')
---> 15 base_model.load_state_dict(load_checkpoint(base_name, device))
17 print('downloading upsampler checkpoint...')
18 upsampler_model.load_state_dict(load_checkpoint('upsample', device))
File ~/point-e/point_e/models/download.py:78, in load_checkpoint(checkpoint_name, device, progress, cache_dir, chunk_size)
72 raise ValueError(
73 f"Unknown checkpoint name {checkpoint_name}. Known names are: {MODEL_PATHS.keys()}."
74 )
75 path = fetch_file_cached(
76 MODEL_PATHS[checkpoint_name], progress=progress, cache_dir=cache_dir, chunk_size=chunk_size
77 )
---> 78 return torch.load(path, map_location=device)
File ~/.local/lib/python3.10/site-packages/torch/serialization.py:797, in load(f, map_location, pickle_module, weights_only, **pickle_load_args)
792 if _is_zipfile(opened_file):
793 # The zipfile reader is going to advance the current file position.
794 # If we want to actually tail call to torch.jit.load, we need to
795 # reset back to the original position.
796 orig_position = opened_file.tell()
--> 797 with _open_zipfile_reader(opened_file) as opened_zipfile:
798 if _is_torchscript_zip(opened_zipfile):
799 warnings.warn("'torch.load' received a zip file that looks like a TorchScript archive"
800 " dispatching to 'torch.jit.load' (call 'torch.jit.load' directly to"
801 " silence this warning)", UserWarning)
File ~/.local/lib/python3.10/site-packages/torch/serialization.py:283, in _open_zipfile_reader.init(self, name_or_buffer)
282 def init(self, name_or_buffer) -> None:
--> 283 super().init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
The text was updated successfully, but these errors were encountered: