如何解决使用torch.load时我的检查点文件出了点问题
当我使用torch.load
加载一个检查点时:
torch.load('./latest_net_G.pth',map_location='cpu')
我遇到了运行时错误:
---------------------------------------------------------------------------
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,**kwargs)
1592
/opt/conda/lib/python3.7/tarfile.py in taropen(cls,**kwargs)
1620 raise ValueError("mode must be 'r','a','w' or 'x'")
-> 1621 return cls(name,**kwargs)
1622
/opt/conda/lib/python3.7/tarfile.py in __init__(self,format,tarinfo,dereference,ignore_zeros,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-15-2abbf3aab3ae> in <module>
----> 1 torch.load('multi_task/checkpoints/latest_pet/latest_net_G.pth.tar',map_location='cpu')
/opt/conda/lib/python3.7/site-packages/torch/serialization.py in load(f,**pickle_load_args)
385 f = f.open('rb')
386 try:
--> 387 return _load(f,**pickle_load_args)
388 finally:
389 if new_fd:
/opt/conda/lib/python3.7/site-packages/torch/serialization.py in _load(f,**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.tar is a zip archive (did you mean to use torch.jit.load()?)
这是我保存模型的方式:
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)
我不知道我的检查点文件出了什么问题。因为实际上我可以成功加载其他检查点文件。另外,我的pytorch版本是1.1.0
。您能帮我解决这个问题吗?
谢谢。
解决方法
我找到了解决方案。由于我使用不同的集群进行训练和调试,因此每个集群的torch
版本是不同的。保存模型时,割炬版本为1.6.0,加载时为1.1.0。
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。