-
Notifications
You must be signed in to change notification settings - Fork 516
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
run 'python model.py' in the demo folder #28
Comments
I can confirm this on my side as well. |
my env is Ubuntu 14.04. Anaconda3 |
pip install blocksparse-1.0.0-py2.py3-none-any.whl there is a error |
@kkshmz |
@prafullasd |
Try using the unoptimized model, it doesnt need you to install blocksparse. Download it from |
You just tell him how to avoid this problem, but not how to solve it. |
there is a error
File "model.py", line 88, in
tf.import_graph_def(graph_def_optimized)
File "/home/lhx/miniconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 432, in new_func
return func(*args, **kwargs)
File "/home/lhx/miniconda3/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 489, in import_graph_def
graph._c_graph, serialized, options) # pylint: disable=protected-access
tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'EdgeBias' in binary running on lhx-910. Make sure the Op and Kernel are registered in the binary running in this process.
The text was updated successfully, but these errors were encountered: