-
I have a model trained on bigdl spark cluster ,and I want this model to load in tf-serving ?
Is there any feasible way to do this?
Current we have tf1 frozen graph in pb model, but I not sure about…
-
**What deployment mode you are use? **
Kuberentes.
**What KubeFATE and FATE version you are using? **
v.1.9.0
**What OS you are using for docker-compse or Kubernetes? Please also clear the v…
-
Platform (like ubuntu 16.04/win10):
Ubuntu14.04
Python version:
2.7
Source framework with version (like Tensorflow 1.4.1 with GPU):
TensorFlow1.4 gpu
Destination framework with version (like CNT…
-
Click to expand!
### Issue Type
Bug
### Source
source
### Tensorflow Version
2.9.1
### Custom Code
No
### OS Platform and Distribution
Linux Ubuntu 20.04
### Mobile device
_No response_…
-
/kind bug
**What steps did you take and what happened:**
When deploying a new version of kserve instance we see that the older revisions are still running even after successful deployment of new…
-
I am able to convert onnx model to tensorflow. However, when I try to access trainable variables/variables from the model, it displays that the attribute is not present. Also, when I try to access the…
-
TF is adopting keras 3, and from TF 2.16 it will by default point to Keras 3. While we can say "users have to switch to tf-keras" to use Mlflow, it's a broken UX. Context: https://github.com/keras-tea…
-
/kind feature
**Describe the solution you'd like**
KFServing is (right now) loosely based on Tensorflow-Serving. One great thing that I like about TFServing is that it has the ability to use gcs b…
-
Currently, the learnt models require the `nwords` parameter, along with the main `words` input, when serving the models with tensorflow server.
It would be very helpful if this requirement of `nwor…
-
This isn't an immediate priority, but it's likely that some users will want some sort of authentication for model serving.
For example, suppose a server is publicly accessible to the internet, serv…