CODEWITHSUNDEEP
pythontensorflowmachine-learningkerasdeep-learning
Mahisha Patel
Mahisha Patel

Reputation: 51

ValueError: Layer model_16 expects 2 input(s), but it received 1 input tensors

I'm trying to use Concatenate() in order to create an ensemble of VGG16 and VGG19. My images are of the shape (224, 224, 3). I do not understand what is this error about.

Here's the code:

# Preprocessing the Training set
train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)

# Preprocessing the Train set
training_set = train_datagen.flow_from_directory('/content/drive/MyDrive/Model Development /tbdataset/Train',
                                                 target_size = (224, 224),
                                                 batch_size = 32,
                                                 class_mode = 'categorical')
# Preprocessing the Test set
test_datagen = ImageDataGenerator(rescale = 1./255)
test_set = test_datagen.flow_from_directory('/content/drive/MyDrive/Model Development /tbdataset/Test',
                                            target_size = (224, 224),
                                            batch_size = 32,
                                            class_mode = 'categorical',
                                            shuffle=False)

vgg19 = VGG19(input_shape=IMAGE_SIZE, weights='imagenet', include_top=False)
for layer in vgg19.layers:
    layer._name = layer._name + str('_19')
    layer.trainable = False

vgg16 = VGG16(input_shape=IMAGE_SIZE, weights='imagenet', include_top=False)
for layer in vgg16.layers:
    layer._name = layer._name + str('_16')
    layer.trainable = False

vgg16_x = Flatten()(vgg16.output)
vgg19_x = Flatten()(vgg19.output)

x = Concatenate()([vgg16_x, vgg19_x])
out = Dense(2, activation='softmax')(x)

model = Model(inputs = [vgg16.input, vgg19.input], outputs = out)
model.compile(
  loss='categorical_crossentropy',
  optimizer=tf.keras.optimizers.Adam(
    learning_rate=0.0005,
    name="Adam"),
  metrics=['accuracy',
           'AUC',
           'Precision',
           'Recall',
  ]
)
model.summary()

r = model.fit(
  training_set,
  validation_data=test_set,
  epochs=20,
  steps_per_epoch=len(training_set),
  validation_steps=len(test_set)
)

I'm getting the following error:

 ValueError: Layer model_16 expects 2 input(s), but it received 1 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None) dtype=float32>]

Can anyone guide me with the above issue? Thank you in advance!

Upvotes: 1

Views: 388

Answers (1)

Marco Cerliani
Marco Cerliani

Reputation: 22021

If vgg16 and vgg19 receive the same input you can use a shared input layer for both. In this way, your model will have only one input.

Here the code:

IMAGE_SIZE = (224,224,3)

vgg19 = tf.keras.applications.vgg19.VGG19(
    input_shape=IMAGE_SIZE, weights='imagenet', include_top=False)
for layer in vgg19.layers:
    layer._name = layer._name + str('_19')
    layer.trainable = False

vgg16 = tf.keras.applications.vgg16.VGG16(
    input_shape=IMAGE_SIZE, weights='imagenet', include_top=False)
for layer in vgg16.layers:
    layer._name = layer._name + str('_16')
    layer.trainable = False

inp = Input(IMAGE_SIZE)
    
vgg16_x = Flatten()(vgg16(inp))
vgg19_x = Flatten()(vgg19(inp))

x = Concatenate()([vgg16_x, vgg19_x])
out = Dense(2, activation='softmax')(x)

model = Model(inputs = inp, outputs = out)
model.compile(
  loss='categorical_crossentropy',
  optimizer=tf.keras.optimizers.Adam(
    learning_rate=0.0005,
    name="Adam"),
  metrics=['accuracy',
           'AUC',
           'Precision',
           'Recall',
  ]
)
model.summary()

Upvotes: 2

Related Questions