Saving A Model That Contains Universal Sentence Encoder as its Embedding - tensorflow

Question

I am trying to save a model which uses USE from tf-hub as its embedding layer and has a few FFN stacked upon it. The model seems to work fine, but I am facing a problem in saving and loading the model.
disable_eager_execution()
embed = hub.Module(module_url)
def UniversalEmbedding(x):
return embed(tf.squeeze(tf.cast(x, tf.string)))
input_text = Input(shape=[], dtype=tf.string)
response_text = Input(shape=[], dtype=tf.string)
text_embedding = Lambda(UniversalEmbedding, output_shape=(512, ))(input_text)
response_embedding = Lambda(UniversalEmbedding, output_shape=(512, ))(response_text)
response_embedding = Dense(512, activation='relu')(response_embedding)
response_embedding = Dense(512, activation='relu')(response_embedding)
score = Dot(axes=1, normalize=True)([text_embedding, response_embedding])
pred = Dense(2, activation='softmax')(score)
text_encoder = Model(inputs=[input_text], outputs=text_embedding)
response_encoder = Model(inputs=[response_text], outputs=response_embedding)
model = Model(inputs=[input_text, response_text], outputs=pred)
The code above is how I built my model (its a dual encoder model with USE as its encoder).
I had to disable eager execution because USE seems to be not working in eager execution environment yet. If not, and if there is a workaround for that, I'd really appreciate any help for this too :)
The model is trained and saved via the following code :
with tf.compat.v1.Session() as session:
K.set_session(session)
session.run(tf.compat.v1.global_variables_initializer())
session.run(tf.compat.v1.tables_initializer())
history = model.fit_generator(generator=train_neg_sample_generator,
validation_data=val_neg_sample_generator, epochs=20,
callbacks=[checkpointer, earlystopper], verbose=0)
and the model is loaded with no error when the weights in the checkpoints (saved in hdf5 files) are loaded to the model defined in the code above. So the code below works fine, only because the architecture 'model' is already defined above.
with tf.compat.v1.Session() as session:
K.set_session(session)
session.run(tf.compat.v1.global_variables_initializer())
session.run(tf.compat.v1.tables_initializer())
model.load_weights('./saved_models/weights.03-0.29.hdf5')
tf.keras.models.save_model(model, 'test_model2.hdf5')
predicts = model.predict([["how are you?", "how are you?", 'hi', 'my two favorites in one pic!'], ["i'm fine", "what the heck", 'hi', 'same!']])
print(predicts)
print(np.argmax(predicts, axis=1))
Then I tried 2 things. First, I tried to save the architecture in json format, load the model architecture and then load the weights, but it did not work. Then I tried to save the whole model via keras.models.save_model, but it did not work either.
In both cases, they returned
AttributeError: module 'tensorflow' has no attribute 'placeholder'
How can I save/load the whole model (if not at once, loading architecture / weight separately is fine too) ?
Here is the whole error log
AttributeError Traceback (most recent call last)
<ipython-input-31-47468f2533ad> in <module>()
1 from keras.models import load_model
2
----> 3 model2 = load_model('testest.h5')
13 frames
/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py in load_wrapper(*args, **kwargs)
456 os.remove(tmp_filepath)
457 return res
--> 458 return load_function(*args, **kwargs)
459
460 return load_wrapper
/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py in load_model(filepath, custom_objects, compile)
548 if H5Dict.is_supported_type(filepath):
549 with H5Dict(filepath, mode='r') as h5dict:
--> 550 model = _deserialize_model(h5dict, custom_objects, compile)
551 elif hasattr(filepath, 'write') and callable(filepath.write):
552 def load_function(h5file):
/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py in _deserialize_model(h5dict, custom_objects, compile)
241 raise ValueError('No model found in config.')
242 model_config = json.loads(model_config.decode('utf-8'))
--> 243 model = model_from_config(model_config, custom_objects=custom_objects)
244 model_weights_group = h5dict['model_weights']
245
/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py in model_from_config(config, custom_objects)
591 '`Sequential.from_config(config)`?')
592 from ..layers import deserialize
--> 593 return deserialize(config, custom_objects=custom_objects)
594
595
/usr/local/lib/python3.6/dist-packages/keras/layers/__init__.py in deserialize(config, custom_objects)
166 module_objects=globs,
167 custom_objects=custom_objects,
--> 168 printable_module_name='layer')
/usr/local/lib/python3.6/dist-packages/keras/utils/generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
145 config['config'],
146 custom_objects=dict(list(_GLOBAL_CUSTOM_OBJECTS.items()) +
--> 147 list(custom_objects.items())))
148 with CustomObjectScope(custom_objects):
149 return cls.from_config(config['config'])
/usr/local/lib/python3.6/dist-packages/keras/engine/network.py in from_config(cls, config, custom_objects)
1041 # First, we create all layers and enqueue nodes to be processed
1042 for layer_data in config['layers']:
-> 1043 process_layer(layer_data)
1044
1045 # Then we process nodes in order of layer depth.
/usr/local/lib/python3.6/dist-packages/keras/engine/network.py in process_layer(layer_data)
1027
1028 layer = deserialize_layer(layer_data,
-> 1029 custom_objects=custom_objects)
1030 created_layers[layer_name] = layer
1031
/usr/local/lib/python3.6/dist-packages/keras/layers/__init__.py in deserialize(config, custom_objects)
166 module_objects=globs,
167 custom_objects=custom_objects,
--> 168 printable_module_name='layer')
/usr/local/lib/python3.6/dist-packages/keras/utils/generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
147 list(custom_objects.items())))
148 with CustomObjectScope(custom_objects):
--> 149 return cls.from_config(config['config'])
150 else:
151 # Then `cls` may be a function returning a class.
/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py in from_config(cls, config)
1101 A layer instance.
1102 """
-> 1103 return cls(**config)
1104
1105 def count_params(self):
/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
/usr/local/lib/python3.6/dist-packages/keras/engine/input_layer.py in __init__(self, input_shape, batch_size, batch_input_shape, dtype, input_tensor, sparse, name)
85 dtype=dtype,
86 sparse=self.sparse,
---> 87 name=self.name)
88 else:
89 self.is_placeholder = False
/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py in placeholder(shape, ndim, dtype, sparse, name)
539 x = tf.sparse_placeholder(dtype, shape=shape, name=name)
540 else:
--> 541 x = tf.placeholder(dtype, shape=shape, name=name)
542 x._keras_shape = shape
543 x._uses_learning_phase = False
AttributeError: module 'tensorflow' has no attribute 'placeholder'

Answer 1

Provide the whole error log, not just a part of it.
If it's really error because of saving then what about model.save('model.h5')?
Not using the module from tf.keras.models but call a methomd from the Model class itself.
But why these code?
with tf.compat.v1.Session() as session:
K.set_session(session)
session.run(tf.compat.v1.global_variables_initializer())
session.run(tf.compat.v1.tables_initializer())
I believe you could juat call model.fit right away, and your tf is version2 right? Why call compat.v1?
Tensorflow 2 doesn't have Placeholder so I think it's maybe about this.

Answer 2

Worked fine with tensorflow version 1.15
Looking forward for tf-hub to become completely compatible with tensorflow 2.0 and keras...