clip-as-service icon indicating copy to clipboard operation
clip-as-service copied to clipboard

when to support Tensorflow2.0?

Open ares5221 opened this issue 5 years ago • 9 comments

Prerequisites

Please fill in by replacing [ ] with [x].

System information

Some of this information can be collected via this script.

  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
  • TensorFlow installed from (source or binary):
  • TensorFlow version:
  • Python version:
  • bert-as-service version:
  • GPU model and memory:
  • CPU model and memory:

Description

Please replace YOUR_SERVER_ARGS and YOUR_CLIENT_ARGS accordingly. You can also write your own description for reproducing the issue.

I'm using this command to start the server:

bert-serving-start YOUR_SERVER_ARGS

and calling the server via:

bc = BertClient(YOUR_CLIENT_ARGS)
bc.encode()

Then this issue shows up:

...

ares5221 avatar Oct 09 '19 02:10 ares5221

I am also looking forward to use Tensorflow 2.0 and would like to use it with BAAS.

Since you are testing it right now, what kind of issue are you facing? You have not yet shared any details about that.

ThomasSchoenbeck avatar Oct 14 '19 12:10 ThomasSchoenbeck

While starting bert server, i got this error:

image

Any idea how to overcome this?

techwithshadab avatar Nov 11 '19 07:11 techwithshadab

While starting bert server, i got this error:

image

Any idea how to overcome this? this is a usual issue,you can search: start fail or other key word in issues, you can find the way to fix it ,like #467

ares5221 avatar Nov 11 '19 07:11 ares5221

any update on support for TF 2.0?

sivakumarch avatar Dec 12 '19 16:12 sivakumarch

After upgrading to TF2 , I'm getting error for server

module 'tensorflow' has no attribute 'logging'

I am assuming this is TF 2 issue.

alidavut avatar Feb 11 '20 05:02 alidavut

Hopefully Bert serving can be compatible with TF-2.0, right now, the workaround for me is to serve the bert model in a different server with TF-1.14

owenljn avatar May 28 '20 16:05 owenljn

Older issue, but is tensorflow>=2.2 support planned?

Seems to come up here and there #580

Downgrade to tensorflow>=1.10 is a fix but unfortunately not possible on python 3.8

oakieoaktree avatar Aug 19 '20 12:08 oakieoaktree

any update on support for TF 2.0?

Akila-Ayanthi avatar Apr 13 '21 14:04 Akila-Ayanthi

why not use Tensorflow serving ......^^

kev216 avatar Jul 26 '21 09:07 kev216