Runtime error while trying basic tensorflow code

Question

Update:

Whether it is a word, sentence or phrase, The Universal Sentence Encoder will always return vector size of 512. I will like to know why 512 and not something else.

The following question was resolved by the answer provided.

I tried the example provided on tensorflow home page:

https://tfhub.dev/google/universal-sentence-encoder/2

I got runtime error like this:

RuntimeError: Exporting/importing meta graphs is not supported when eager execution is enabled. No graph exists when eager execution is enabled.

The code that I tried is:

import tensorflow.compat.v1 as tf
import tensorflow_hub as hub

config = tf.ConfigProto()
session = tf.Session(config=config)

embed = hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2")
embeddings = embed(
    [
        "The quick brown fox jumps over the lazy dog.",
        "I am a sentence for which I would like to get its embedding",
    ]
)

print(session.run(embeddings))

How to run this code correctly?

is this question not active anymore? why don't you delete it then. or put an update at the top of it — eugen
– eugen, Commented Oct 3, 2019 at 16:00

Yosi Dahari · Accepted Answer · 2019-10-01 06:31:45Z

6

It's a matter of the tensorflow version you are using.

In Tensorflow 2.0 you should use hub.load() or hub.KerasLayer().

answered Oct 1, 2019 at 6:31

Yosi Dahari

7,0395 gold badges26 silver badges48 bronze badges

Sign up to request clarification or add additional context in comments.

3 Comments

shantanuo Over a year ago

ValueError: Non-callable result from hub.load # Can you show how to create "session" object?

shantanuo Over a year ago

Thanks for the answer. But I have a follow up question. Please see the update.

bobthemac Over a year ago

@shantanuo if you have a follow up question it should be asked as its own question, you will have more luck getting an answer.

Ashwin Geet D'Sa · Accepted Answer · 2021-05-19 10:34:07Z

1

Based on a discussion from github: https://github.com/tensorflow/hub/issues/350

The below solution worked for me:

import tensorflow.compat.v1 as tf
tf.disable_eager_execution()

The above code disables the eager execution.

answered May 19, 2021 at 10:34

Ashwin Geet D'Sa

7,4583 gold badges40 silver badges66 bronze badges

Collectives™ on Stack Overflow

Runtime error while trying basic tensorflow code

2 Answers 2

3 Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

3 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related