Running Demo fails (possibly corrupted model parameters?)

[michael-camilleri]

I am attempting to run the demo, using: fcos https://github.com/lzrobots/Mouse_Det/raw/master/demo/images/COCO_val2014_000000000885.jpg

However, this fails as follows:

Traceback (most recent call last):
  File "/home/s1238640/miniconda3/envs/py3phd/bin/fcos", line 7, in <module>
    exec(compile(f.read(), __file__, 'exec'))
  File "/home/s1238640/Documents/Code/FCOS/fcos/bin/fcos", line 36, in <module>
    cpu_only=not torch.cuda.is_available()  # if you do not have GPUs, please set cpu_only as True
  File "/home/s1238640/Documents/Code/FCOS/fcos/fcos.py", line 192, in __init__
    _ = checkpointer.load(cfg.MODEL.WEIGHT)
  File "/home/s1238640/Documents/Code/FCOS/fcos_core/utils/checkpoint.py", line 61, in load
    checkpoint = self._load_file(f)
  File "/home/s1238640/Documents/Code/FCOS/fcos_core/utils/checkpoint.py", line 136, in _load_file
    loaded = super(DetectronCheckpointer, self)._load_file(f)
  File "/home/s1238640/Documents/Code/FCOS/fcos_core/utils/checkpoint.py", line 95, in _load_file
    return torch.load(f, map_location=torch.device("cpu"))
  File "/home/s1238640/miniconda3/envs/py3phd/lib/python3.7/site-packages/torch/serialization.py", line 529, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "/home/s1238640/miniconda3/envs/py3phd/lib/python3.7/site-packages/torch/serialization.py", line 709, in _legacy_load
    deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF, expected 77184 more bytes. The file might be corrupted.

It appears that it is unable to load the model parameters. Has this been encountered before?