clip-as-service
clip-as-service copied to clipboard
when to support Tensorflow2.0?
Prerequisites
Please fill in by replacing
[ ]
with[x]
.
- [x] Are you running the latest
bert-as-service
? - [x] Did you follow the installation and the usage instructions in
README.md
? - [x] Did you check the FAQ list in
README.md
? - [x] Did you perform a cursory search on existing issues?
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
andYOUR_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:
...
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.
While starting bert server, i got this error:
Any idea how to overcome this?
While starting bert server, i got this error:
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
any update on support for TF 2.0?
After upgrading to TF2 , I'm getting error for server
module 'tensorflow' has no attribute 'logging'
I am assuming this is TF 2 issue.
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
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
any update on support for TF 2.0?
why not use Tensorflow serving ......^^