RuntimeError: storage has wrong size: expected 0 got 64

[theRealSuperMario]

I am getting an error when trying to load the checkpoint I trained with the first-order motion model. A quick google search suggests that the pytorch version might cause checkpoints to be corrupted

pytorch/pytorch#12042

I am still investigating my problem, however, I just want to ask if you had encountered if before.

[AliaksandrSiarohin]

No didn't have it. Have you specified firtst order model flag?

[theRealSuperMario]

Have you specified firtst order model flag?

I am not sure what you mean by it. Can you point me somewhere?

[theRealSuperMario]

So I tried and a simple torch.load(path.pth.tar) gives the error

[AliaksandrSiarohin]

And what is your torch version?

[theRealSuperMario]

backcall==0.2.0
certifi==2020.6.20
cffi==1.11.5
cloudpickle==0.5.3
cycler==0.10.0
dask==0.18.2
decorator==4.3.0
future==0.18.2
imageio==2.3.0
ipython==7.16.1
ipython-genutils==0.2.0
jedi==0.17.1
kiwisolver==1.0.1
matplotlib==2.2.2
mkl-fft==1.1.0
mkl-random==1.1.1
mkl-service==2.3.0
mock==4.0.1
networkx==2.1
numpy==1.15.0
olefile==0.46
pandas==0.23.4
parso==0.7.0
pexpect==4.8.0
pickleshare==0.7.5
Pillow==5.2.0
prompt-toolkit==3.0.5
ptyprocess==0.6.0
pudb==2019.2
pycparser==2.18
pygit==0.1
Pygments==2.6.1
pyparsing==2.2.0
python-dateutil==2.7.3
pytz==2018.5
PyWavelets==0.5.2
PyYAML==5.1
scikit-image==0.14.0
scikit-learn==0.19.2
scipy==1.1.0
six==1.15.0
toolz==0.9.0
torch==1.0.0
torchvision==0.2.1
tqdm==4.24.0
traitlets==4.3.3
urwid==2.1.0
wcwidth==0.2.5

torch==1.0.0
torchvision==0.2.1

[AliaksandrSiarohin]

Have you tried to download checkpoint aggain, maybe from a different place yandex-disk? What is the weight in Mb of the ckp?