Replies: 1 comment
-
Hi,
I guess that’s because the deeper-kit version you used to freeze the model and that you used to load the model are different.
————————
Jinzhe Zeng
PhD student in Chemistry
Rutgers University
[email protected]
CV: https://njzjz.win/cv
… On Feb 26, 2020, at 06:50, r-hou ***@***.***> wrote:
I installed deepmd-kit completely following the instructions on the main page. However, deepmd-kit cannot load a frozen model and gives the error message as follows:
tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'DescrptNorot' in binary running on dirac.phys.ust.hk. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) tf.contrib.resampler should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
njzjz
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I installed deepmd-kit completely following the instructions on the main page. However, deepmd-kit cannot load a frozen model and gives the error message as follows:
tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'DescrptNorot' in binary running on dirac.phys.ust.hk. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.)
tf.contrib.resampler
should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.Beta Was this translation helpful? Give feedback.
All reactions