Skip to content
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

Encountered an error while loading tensorflow savedmodel #47

Closed
Whitessky opened this issue Jan 21, 2019 · 1 comment
Closed

Encountered an error while loading tensorflow savedmodel #47

Whitessky opened this issue Jan 21, 2019 · 1 comment

Comments

@Whitessky
Copy link

While TRTIS loading tensorflow savedmodel,an error occurred like this:
Loading servable: {name: road-tensorflow version: 1} failed: Not found: Op type not registered 'PyFunc' in binary running on efa5e12b876b. 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.resamplershould be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
what did it mean and what should i do? thanks!

@deadeyegoodwin
Copy link
Contributor

It looks like your model requires a custom tensorflow operation. That operation is implemented by wrapping a python function. See https://www.tensorflow.org/api_docs/python/tf/py_func.
Currently TRTIS does not support custom tensorflow operations. Only operations that are included in the tensorflow build are included. Can you implement the custom functionality using standard TF operations?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

No branches or pull requests

2 participants