trying to run prompt but hitting error
Opened this issue · 5 comments
Hi,
I'm training this model on a dataset of pictures of rooms, and running this prompt - "photo of a room".
But, I'm hitting this issue -
RuntimeError: PytorchStreamReader failed reading file data/2: file read failed
Model has been running for nearly the entire day, what exactly is wrong here?
full logs:
Traceback (most recent call last): File "/usr/local/bin/imagen", line 8, in <module> sys.exit(imagen()) File "/usr/local/lib/python3.7/dist-packages/click/core.py", line 829, in __call__ return self.main(*args, **kwargs) File "/usr/local/lib/python3.7/dist-packages/click/core.py", line 782, in main rv = self.invoke(ctx) File "/usr/local/lib/python3.7/dist-packages/click/core.py", line 1066, in invoke return ctx.invoke(self.callback, **ctx.params) File "/usr/local/lib/python3.7/dist-packages/click/core.py", line 610, in invoke return callback(*args, **kwargs) File "/usr/local/lib/python3.7/dist-packages/imagen_pytorch/cli.py", line 32, in imagen loaded = torch.load(str(model_path)) File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 712, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 1049, in _load result = unpickler.load() File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 1019, in persistent_load load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 997, in load_tensor storage = zip_file.get_storage_from_record(name, numel, torch._UntypedStorage).storage()._untyped() RuntimeError: PytorchStreamReader failed reading file data/2: file read failed
Hmm, I’m just downloading your repo and running it on the dataset. How would you suggest I proceed on this?
can you paste your full command line?