Open czero69 opened 5 years ago
i have meet the same problem,are you solved it ?
replacing
self._backend = type2backend[type(input)]
withself._backend = type2backend[input.type()]
solved the problem
thanks so much .
Ty
thanks
thanks
Did it like you did, but there was a new error.
True
Traceback (most recent call last):
File "demo.py", line 275, in
Is this the need to define the subclass SpatialAdaptiveMaxPooling_updateOutput? Could anybody help me?
I also have the same problem with Pytorch 1.1 and Windows. Perhaps downgrading to pytorch 0.4 solves the problem.
How to downgrade to pytorch 0.4?Remove Pytorch 1.1 and install pytorch 0.4 ?
I am not the best person to recommend but: I would create a new virtual environment and install all required packages.
If you are using conda, conda create - n yourenvname python=x.x source activate yourenvname
and then install all packages you need with
conda install yourpackage1
And then install the pytorch version that are used in this repo.
On Wed, 17 Jul 2019, 08:49 Fansgithub2019, notifications@github.com wrote:
How to downgrade to pytorch 0.4?Remove Pytorch 1.1 and install pytorch 0.4 ?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/detectRecog/CCPD/issues/17?email_source=notifications&email_token=AKOJJ3DBFXSKOVDTDTIE2PTP73FIRA5CNFSM4GL3T3T2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD2DLD3Q#issuecomment-512143854, or mute the thread https://github.com/notifications/unsubscribe-auth/AKOJJ3GKVIRSEISWE4G2ATLP73FIRANCNFSM4GL3T3TQ .
I got error in roi pooling for return self.backends[name].load(), while trying to run demo.py. my env:
replacing
self._backend = type2backend[type(input)]
withself._backend = type2backend[input.type()]
solved the problemI suspect I have newer pytorch. See also: https://discuss.pytorch.org/t/keyerror-class-torch-tensor/22560
full error code: