semantic-segmentation: tarfile.EmptyHeaderError: empty header

Hi

I am having a problem when I try to run the demo.py. When I run the following command:

python3 demo.py --demo-image test.png --snapshot pretrained_models/cityscapes_best.pth

I get the error:

Using regular batch norm
Net built.
Traceback (most recent call last):
  File "/usr/lib/python3.6/tarfile.py", line 2297, in next
    tarinfo = self.tarinfo.fromtarfile(self)
  File "/usr/lib/python3.6/tarfile.py", line 1093, in fromtarfile
    obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
  File "/usr/lib/python3.6/tarfile.py", line 1029, in frombuf
    raise EmptyHeaderError("empty header")
tarfile.EmptyHeaderError: empty header

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 595, in _load
    return legacy_load(f)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 506, in legacy_load
    with closing(tarfile.open(fileobj=f, mode='r:', format=tarfile.PAX_FORMAT)) as tar, \
  File "/usr/lib/python3.6/tarfile.py", line 1589, in open
    return func(name, filemode, fileobj, **kwargs)
  File "/usr/lib/python3.6/tarfile.py", line 1619, in taropen
    return cls(name, mode, fileobj, **kwargs)
  File "/usr/lib/python3.6/tarfile.py", line 1482, in __init__
    self.firstmember = self.next()
  File "/usr/lib/python3.6/tarfile.py", line 2312, in next
    raise ReadError("empty file")
tarfile.ReadError: empty file

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "demo.py", line 32, in <module>
    net, _ = restore_snapshot(net, optimizer=None, snapshot=args.snapshot, restore_optimizer_bool=False)
  File "/home/sieuwe/Downloads/semantic-segmentation-master/optimizer.py", line 69, in restore_snapshot
    checkpoint = torch.load(snapshot, map_location=torch.device('cpu'))
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 426, in load
    return _load(f, map_location, pickle_module, **pickle_load_args)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 597, in _load
    if _is_zipfile(f):
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 75, in _is_zipfile
    if ord(magic_byte) != ord(read_byte):
TypeError: ord() expected a character, but string of length 0 found

I believe the error accours when it is loading the pretrained_models/wider_resnet38.pth.tar. But I dont know what I have done wrong.

The steps I followed where:

• clone repo
• Install all dependencies
• download cityscapes_best.pth and wider_resnet38.pth.tar
• make a folder called pretrained_models in repo root and add the two mentioned files.
• type above mentioned command to run demo.

My system Ubuntu 18.4 LTS python 3.6 Cuda 10.2 Driver 440.33.01 card GTX1080

PS: I am also wondering if there is a python video implementation for this network which can take a normal video as input? Because the Demo.py is only for images right? Or can I make a loop which loops over a video and per frame makes a prediction using the net(img) function. If that is possible what will the FPS be for such an implementation on a GTX1080?

Thanks

Sieuwe