'Sequential' object has no attribute '_is_graph_network' when exporting Keras model to TensorFlow

Question

I'm trying to export a Keras model to TensorFlow.

Keras Version 2.1.4 TF Version 1.3.0 Numpy Version 1.13.3

This is the model:

img_width, img_height = 150, 150
batch_size = 32
samples_per_epoch = 1000
validation_steps = 300
nb_filters1 = 32
nb_filters2 = 64
conv1_size = 3
conv2_size = 2
pool_size = 2
classes_num = 3
lr = 0.0004

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(img_width, img_height, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())  # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Dense(classes_num, activation='softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer=optimizers.RMSprop(lr=lr),
metrics=['accuracy'])

This is the export code:

from tensorflow.python import keras
estimator_model = keras.estimator.model_to_estimator(keras_model=model)

This is the error:

INFO:tensorflow:Using the Keras model provided. INFO:tensorflow:Using default config. WARNING:tensorflow:Using temporary folder as model directory: /home/dsxuser/.tmp/tmpbgYQQa INFO:tensorflow:Using config: {'_save_checkpoints_secs': 600, '_session_config': None, '_keep_checkpoint_max': 5, '_task_type': 'worker', '_global_id_in_cluster': 0, '_is_chief': True, '_cluster_spec': , '_evaluation_master': '', '_save_checkpoints_steps': None, '_keep_checkpoint_every_n_hours': 10000, '_service': None, '_num_ps_replicas': 0, '_tf_random_seed': None, '_master': '', '_num_worker_replicas': 1, '_task_id': 0, '_log_step_count_steps': 100, '_model_dir': '/home/dsxuser/.tmp/tmpbgYQQa', '_save_summary_steps': 100}

AttributeErrorTraceback (most recent call last) in () 1 from tensorflow.python import keras ----> 2 estimator_model = keras.estimator.model_to_estimator(keras_model=model)

/opt/conda/envs/DSX-Python27/lib/python2.7/site-packages/tensorflow/python/keras/_impl/keras/estimator.pyc in model_to_estimator(keras_model, keras_model_path, custom_objects, model_dir, config) 476 477 keras_weights = keras_model.get_weights() --> 478 if keras_model._is_graph_network: 479 # TODO(yifeif): move checkpoint initialization to scaffold.init_fn 480 _save_first_checkpoint(keras_model,

AttributeError: 'Sequential' object has no attribute '_is_graph_network'

Any ideas?

Answer 1

You need this from tensorflow.python.keras import Sequential you should use keras api implemented in tensorflow instead of using keras api directly.