ZoeDepth icon indicating copy to clipboard operation
ZoeDepth copied to clipboard

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

Open michaeltan53 opened this issue 1 year ago • 0 comments

I received an error message like this when generating depth map with ZoeD model running on Linux

Using pretrained resource url::https://github.com/isl-org/ZoeDepth/releases/download/v1.0/ZoeD_M12_K.pt Traceback (most recent call last): File "depth_predict.py", line 19, in model_zoe_k = build_model(conf) File "/home/s_234712236/ZoeDepth/zoedepth/models/builder.py", line 51, in build_model return get_version(config.version_name).build_from_config(config) File "/home/s_234712236/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py", line 253, in build_from_config return ZoeDepth.build(**config) File "/home/s_234712236/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py", line 248, in build model = load_state_from_resource(model, pretrained_resource) File "/home/s_234712236/ZoeDepth/zoedepth/models/model_io.py", line 84, in load_state_from_resource return load_state_dict_from_url(model, url, progress=True) File "/home/s_234712236/ZoeDepth/zoedepth/models/model_io.py", line 60, in load_state_dict_from_url state_dict = torch.hub.load_state_dict_from_url(url, map_location='cpu', **kwargs) File "/opt/conda/lib/python3.8/site-packages/torch/hub.py", line 764, in load_state_dict_from_url return torch.load(cached_file, map_location=map_location, weights_only=weights_only) File "/opt/conda/lib/python3.8/site-packages/torch/serialization.py", line 1004, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "/opt/conda/lib/python3.8/site-packages/torch/serialization.py", line 456, in init super().init(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

Why does it happen and how can I solve it? Many thanks.

michaeltan53 avatar May 11 '24 10:05 michaeltan53