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

Running TFX/tutorials/serving/rest_simple.ipynb on Colab is returning ConnectionError

dennymarcels opened this issue · comments

commented

System information

Current Google Colab environment

Describe the problem

Running this tutorial on Colab is returning ConnectionError: HTTPConnectionPool(host='localhost', port=8501): Max retries exceeded with url: /v1/models/fashion_model:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fddc00a8310>: Failed to establish a new connection: [Errno 111] Connection refused'))
Since I am trying to implement the tutorial with my own code, I am stuck at the request stage.

Exact Steps to Reproduce

Just run the tutorial.

@dennymarcels,

Looks like this is duplicate of issue #2012.

As a workaround, downgrade tensorflow-model-server from 2.10.0 to 1.15.0.

In Install TensorFlow Serving section of the notebook, please uncomment !{SUDO_IF_NEEDED} apt-get install tensorflow-model-server line and add below lines.

Code to install tensorflow-model-server 1.15.0:

!wget 'http://storage.googleapis.com/tensorflow-serving-apt/pool/tensorflow-model-server-1.15.0/t/tensorflow-model-server/tensorflow-model-server_1.15.0_all.deb'
!dpkg -i tensorflow-model-server_1.15.0_all.deb
!pip3 install tensorflow-serving-api==1.15

Sharing the working gist file for reference. Can you please close this issue, since it is already being tracked on #2012.
Thank you!

commented

Hi there, thank you very much for the reply.
I did install actually version 2.8.0 as suggested in #2012 and it is back to work! :)