Keras model exported as TensorFlow model doesn't work with TensorFlow serving about examples HOT 8 CLOSED

I don't think we ever solved this, did we? Have there been any updates that would make this straightforward?

from examples.

/cc @lakshmanok @nfiedel @rhaertel80

from examples.

Could this be an issue with different versions of TF used for training and serving?

from examples.

It's unlikely. I ensured that both training and serving were done using tensorflow version 1.5.x

I did have a different error when I trained using TF 1.4 and served using TF 1.5.

from examples.

The TF serving images in Kubeflow are all 1.4 currently. I haven't tried creating a saved model with Keras in TF 1.5, but from my experience, creating an Estimator with TF 1.5 caused failures in TF serving 1.4. Not sure if Keras suffers from a similar issue with compatibility, although your case is the reverse. Did you try 1.4 for both training and serving?

I was able to run this one successfully with TF 1.4 training and serving.
https://github.com/google-aai/tf-serving-k8s-tutorial/blob/master/keras_resnet_serving_solution.ipynb

Here's the client to call the server:
https://github.com/google-aai/tf-serving-k8s-tutorial/blob/master/client/resnet_client.py

from examples.

The notebook link above is broken after a github update. I have an updated notebook here which includes not only creating servable models, but also some guidance on unit testing the input-output API: https://github.com/google-aai/tf-serving-k8s-tutorial/blob/master/keras_training_to_serving_solution.ipynb

from examples.

Created an issue: #48

from examples.

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

from examples.