Error occurred in the Named Entity Recognition using Transformers example

[sitammeur]

trafficstars

Issue Type

Bug

Source

source

Keras Version

Keras 3.1.0.dev2024031303

Custom Code

No

OS Platform and Distribution

No response

Python version

No response

GPU model and memory

Colab T4

Current Behavior?

A bug happened in the ner_model.fit part!

ner_model.compile(optimizer="adam", loss=loss)
ner_model.fit(train_dataset, epochs=10)


def tokenize_and_convert_to_ids(text):
    tokens = text.split()
    return lowercase_and_convert_to_ids(tokens)


# Sample inference using the trained model
sample_input = tokenize_and_convert_to_ids(
    "eu rejects german call to boycott british lamb"
)
sample_input = tf.reshape(sample_input, shape=[1, -1])
print(sample_input)

output = ner_model.predict(sample_input)
prediction = np.argmax(output, axis=-1)[0]
prediction = [mapping[i] for i in prediction]

# eu -> B-ORG, german -> B-MISC, british -> B-MISC
print(prediction)

Output showing like this

OperatorNotAllowedInGraphError: Exception encountered when calling Softmax.call().

Using a symbolic `tf.Tensor` as a Python `bool` is not allowed. You can attempt the following resolutions to the problem: If you are running in Graph mode, use Eager execution mode or decorate this function with @tf.function. If you are using AutoGraph, you can try decorating this function with @tf.function. If that does not work, then you may be using an unsupported feature or your source code may not be visible to AutoGraph. See https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/autograph/g3doc/reference/limitations.md#access-to-source-code for more information.

Arguments received by Softmax.call():
  • inputs=tf.Tensor(shape=(None, 4, None, None), dtype=float32)
  • mask=None

For model training, I anticipate that model.fit will function properly and error-free. But the error happened.

Standalone code to reproduce the issue or tutorial link

Here is an executable Colab link to reproduce the error: https://colab.research.google.com/drive/1WtG-3b78mJHppCptt_GwNKR97KiR_FwU?usp=sharing

Relevant log output

OperatorNotAllowedInGraphError: Exception encountered when calling Softmax.call().

Using a symbolic `tf.Tensor` as a Python `bool` is not allowed. You can attempt the following resolutions to the problem: If you are running in Graph mode, use Eager execution mode or decorate this function with @tf.function. If you are using AutoGraph, you can try decorating this function with @tf.function. If that does not work, then you may be using an unsupported feature or your source code may not be visible to AutoGraph. See https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/autograph/g3doc/reference/limitations.md#access-to-source-code for more information.

Arguments received by Softmax.call():
  • inputs=tf.Tensor(shape=(None, 4, None, None), dtype=float32)
  • mask=None