tensorflow / serving

A flexible, high-performance serving system for machine learning models

Home Page:https://www.tensorflow.org/serving

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

TensorFlow serving seems to have no version attribute

zhangggzh opened this issue · comments

I built and installed the whl package for serving on ROCM myself, but found that only the pip list method was used to view the version of serving, while the " import tensorflow_serving tenorflow_ serving.__ version__ " An error was reported, TensorFlow serving does not have the version attribute. May I ask if this attribute was not added to the source code during development

@zhangggzh, Can you try using below command to check TF Serving version. Thank you!

tensorflow_model_server --version

For docker image you can do this:

docker run --rm -it tensorflow/serving tensorflow_model_server --version

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.

@singhniraj08 Hello, can you add the version attribute in Python? For example, after entering the Python environment, use " tensorflow_ serving__.version__ " to return the version information of serving