search

bio-ontology-research-group / deepgo2

BSD 3-Clause "New" or "Revised" License
25 stars 3 forks source link

RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory #1

Closed roo-kie12 closed 6 months ago

roo-kie12 commented 6 months ago

According to README, I installed the dependencies, downloaded the data.tar.gz file and extracted it successfully. Then I follow the order, run the model with python predict.py -if data/example.fa ,but encountered an error: RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory.

Traceback (most recent call last): File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/esm/pretrained.py", line 33, in load_hub_workaround data = torch.hub.load_state_dict_from_url(url, progress=False, map_location="cpu") File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/torch/hub.py", line 750, in load_state_dict_from_url return torch.load(cached_file, map_location=map_location) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/torch/serialization.py", line 797, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/torch/serialization.py", line 283, in init super().init(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/data/home/jianglab/deepgo2/predict.py", line 88, in main() File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/click/core.py", line 1157, in call return self.main(args, kwargs) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/click/core.py", line 1078, in main rv = self.invoke(ctx) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/click/core.py", line 1434, in invoke return ctx.invoke(self.callback, ctx.params) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/click/core.py", line 783, in invoke return __callback(args, **kwargs) File "/data/home/jianglab/deepgo2/predict.py", line 33, in main proteins, data = extract_esm(in_file, out_file=out_file_esm, device=device) File "/data/home/jianglab/deepgo2/deepgo/extract_esm.py", line 60, in extract_esm model, alphabet = pretrained.load_model_and_alphabet(model_location) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/esm/pretrained.py", line 28, in load_model_and_alphabet return load_model_and_alphabet_hub(model_name) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/esm/pretrained.py", line 63, in load_model_and_alphabet_hub model_data, regression_data = _download_model_and_regression_data(model_name) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/esm/pretrained.py", line 54, in _download_model_and_regression_data model_data = load_hub_workaround(url) File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/esm/pretrained.py", line 37, in load_hub_workaround data = torch.load( File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/torch/serialization.py", line 797, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "/data/home/jianglab/.conda/envs/deepgose/lib/python3.10/site-packages/torch/serialization.py", line 283, in init super().init(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

coolmaksat commented 6 months ago

Hello, it seems that something went wrong while downloading esm model. Could you please try to clean your TORCH_HOME and restart the script?

roo-kie12 commented 6 months ago

Hello, it seems that something went wrong while downloading esm model. Could you please try to clean your TORCH_HOME and restart the script?

Many thanks! In TORCH_HOME, I found the esm model was not downloaded in its entirely. I cleaned the TORCH_HOME and restarted the script, and It works now.