Error while using CPU for segmentation- "NET ERROR: PytorchStreamReader failed reading zip archive: failed finding central directory" Show
When I try segmentation using CPU, I am getting the error- "NET ERROR: PytorchStreamReader failed reading zip archive: failed finding central directory" I can't check if it works using GPU because my graphics card compute capacity seems to be incompatible with pytorch
Windows 10 OS, and NVIDIA GEforce GT730
can you try deleting your models folder and redownloading them? there may have been an interruption during download (see this issue: https://github.com/pytorch/pytorch/issues/31620)? the models folder is in your home directory going to close issue for now please comment if it's still not working Hey everyone... I've been really looking forward to trying out DiscoDiffusion for quite some time now. I finally sat down to give it a go but I'm getting some error messages and am not sure how to fix it. Any one have an idea what these errors refer to and how I can remedy them? RuntimeError Traceback (most recent call last) <ipython-input-15-c43607be9a63> in <module>() 160 print('Prepping model...') 161 model, diffusion = create_model_and_diffusion(**model_config) --> 162 model.load_state_dict(torch.load(f'{model_path}/{diffusion_model}.pt', map_location='cpu')) 163 model.requires_grad_(False).eval().to(device) 164 for name, param in model.named_parameters(): 1 frames/usr/local/lib/python3.7/dist-packages/torch/serialization.py in __init__(self, name_or_buffer) 240 class _open_zipfile_reader(_opener): 241 def __init__(self, name_or_buffer) -> None: --> 242 super(_open_zipfile_reader, self).__init__(torch._C.PyTorchFileReader(name_or_buffer)) 243 244 RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory I’m trying to run Disco Diffusion v5 with basically default settings and getting this error when I try to create the image. Does anyone know how to fix this? My way to solve this problem is to delete folder ‘AI’ in google Drive and run it all again. I guess the problem may be caused by an incomplete pre-traning model
that was not downloaded correctly by the first run, which prevents the correct version of the model from being downloaded. If you have better answer, please add a comment about this, thank you! Pytoch reports an error: PytorchStreamReader failed reading zip archive: failed finding central directory Error reporting position An error is reported if the pre training model is not downloaded
Solution: Delete the file C:\Users\Username/.cache\torch\hub\checkpoints.pth Read More: |