Script to convert Keras models to TensorFlow Serving SavedModel format

export_saved_model.py

import tensorflow as tf

# The export path contains the name and the version of the model
tf.keras.backend.set_learning_phase(0)  # Ignore dropout at inference
model = tf.keras.models.load_model('./inception.h5')
export_path = '../my_image_classifier/1'

# Fetch the Keras session and save the model
# The signature definition is defined by the input and output tensors
# And stored with the default serving key
with tf.keras.backend.get_session() as sess:
    tf.saved_model.simple_save(
        sess,
        export_path,
        inputs={'input_image': model.input},
        outputs={t.name: t for t in model.outputs})

I get the following error:

RuntimeError: Attempted to use a closed Session.

I get the same error
RuntimeError: Attempted to use a closed Session.

solved..

with keras.backend.get_session() as sess:
         tf.saved_model.simple_save(
              sess,
              export_path,
              inputs={'input_image': model.input},
              outputs={t.name: t for t in model.outputs}
        )

the last line break is needed

I got the error - AttributeError: 'list' object has no attribute 'dtype'

I have the same error as @i-amgeek , how do I solve this?