Hi, I have a problem loading my checkpoint file(.pth). It’s all right when I load my other checkpoint files but not with this. Here’s how I save the model:
def save_networks(self, epoch):
"""Save all the networks to the disk.
Parameters:
epoch (int) -- current epoch; used in the file name '%s_net_%s.pth' % (epoch, name)
"""
for name in self.model_names:
if isinstance(name, str):
save_filename = '%s_net_%s.pth' % (epoch, name)
save_path = os.path.join(self.save_dir, save_filename)
net = getattr(self, 'net' + name)
if len(self.gpu_ids) > 0 and torch.cuda.is_available():
if name == 'Rgr':
torch.save(net.state_dict(), save_path)
else:
torch.save(net.module.cpu().state_dict(), save_path)
net.cuda(self.gpu_ids[0])
else:
if name == 'Rgr':
torch.save(net.state_dict(), save_path)
else:
torch.save(net.cpu().state_dict(), save_path)
And when I load the file:
torch.load('./latest_net_G.pth', map_location='cpu')
I got the following error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/opt/conda/lib/python3.7/tarfile.py in nti(s)
186 s = nts(s, "ascii", "strict")
--> 187 n = int(s.strip() or "0", 8)
188 except ValueError:
ValueError: invalid literal for int() with base 8: '_v2\nq\x03(('
During handling of the above exception, another exception occurred:
InvalidHeaderError Traceback (most recent call last)
/opt/conda/lib/python3.7/tarfile.py in next(self)
2288 try:
-> 2289 tarinfo = self.tarinfo.fromtarfile(self)
2290 except EOFHeaderError as e:
/opt/conda/lib/python3.7/tarfile.py in fromtarfile(cls, tarfile)
1094 buf = tarfile.fileobj.read(BLOCKSIZE)
-> 1095 obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
1096 obj.offset = tarfile.fileobj.tell() - BLOCKSIZE
/opt/conda/lib/python3.7/tarfile.py in frombuf(cls, buf, encoding, errors)
1036
-> 1037 chksum = nti(buf[148:156])
1038 if chksum not in calc_chksums(buf):
/opt/conda/lib/python3.7/tarfile.py in nti(s)
188 except ValueError:
--> 189 raise InvalidHeaderError("invalid header")
190 return n
InvalidHeaderError: invalid header
During handling of the above exception, another exception occurred:
ReadError Traceback (most recent call last)
/opt/conda/lib/python3.7/site-packages/torch/serialization.py in _load(f, map_location, pickle_module, **pickle_load_args)
555 try:
--> 556 return legacy_load(f)
557 except tarfile.TarError:
/opt/conda/lib/python3.7/site-packages/torch/serialization.py in legacy_load(f)
466
--> 467 with closing(tarfile.open(fileobj=f, mode='r:', format=tarfile.PAX_FORMAT)) as tar, \
468 mkdtemp() as tmpdir:
/opt/conda/lib/python3.7/tarfile.py in open(cls, name, mode, fileobj, bufsize, **kwargs)
1590 raise CompressionError("unknown compression type %r" % comptype)
-> 1591 return func(name, filemode, fileobj, **kwargs)
1592
/opt/conda/lib/python3.7/tarfile.py in taropen(cls, name, mode, fileobj, **kwargs)
1620 raise ValueError("mode must be 'r', 'a', 'w' or 'x'")
-> 1621 return cls(name, mode, fileobj, **kwargs)
1622
/opt/conda/lib/python3.7/tarfile.py in __init__(self, name, mode, fileobj, format, tarinfo, dereference, ignore_zeros, encoding, errors, pax_headers, debug, errorlevel, copybufsize)
1483 self.firstmember = None
-> 1484 self.firstmember = self.next()
1485
/opt/conda/lib/python3.7/tarfile.py in next(self)
2300 elif self.offset == 0:
-> 2301 raise ReadError(str(e))
2302 except EmptyHeaderError:
ReadError: invalid header
During handling of the above exception, another exception occurred:
RuntimeError Traceback (most recent call last)
<ipython-input-10-c2a19cc36006> in <module>
----> 1 torch.load('multi_task/checkpoints/latest_pet/latest_net_G.pth', map_location=torch.device('cpu'))
/opt/conda/lib/python3.7/site-packages/torch/serialization.py in load(f, map_location, pickle_module, **pickle_load_args)
385 f = f.open('rb')
386 try:
--> 387 return _load(f, map_location, pickle_module, **pickle_load_args)
388 finally:
389 if new_fd:
/opt/conda/lib/python3.7/site-packages/torch/serialization.py in _load(f, map_location, pickle_module, **pickle_load_args)
558 if zipfile.is_zipfile(f):
559 # .zip is used for torch.jit.save and will throw an un-pickling error here
--> 560 raise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)".format(f.name))
561 # if not a tarfile, reset file offset and proceed
562 f.seek(0)
RuntimeError: multi_task/checkpoints/latest_pet/latest_net_G.pth is a zip archive (did you mean to use torch.jit.load()?)
I don’t know what mistakes I have made when saving the model. Could you help me with this?