1
$\begingroup$

I am working in deep learning project using vgg16. I got the following error and I could not solve it.

RuntimeError: ('The name "block1_conv1" is used 2 times in the model. All layer names should be unique.

The code:

vgg16_model = keras.applications.vgg16.VGG16()

input_layer1 = vgg16_model.input
vgg16_model.get_layer(index = 0).name = 'input1'
last_layer1 = vgg16_model.get_layer('flatten').output

# Adding layers
x = Dense(2048, activation='relu', name='fc1')(last_layer1)
x = BatchNormalization(name='bn1')(x)
fc12 = Dense(2048, activation='relu', name='fc2')(x)
bn12 = BatchNormalization(name='bn2')(fc12)
out1 = Dropout(0.4, name='dropout1')(bn12)

#Classification layer
output_layer1 = Dense(no_classes, activation='softmax', name='prediction1')(out1) #106 classes
model1 = Model(input_layer1, output_layer1)

#Train the last block
model1.trainable = True
set_trainable = False
for layer in model1.layers:
    if layer.name == 'block5_conv1':
        set_trainable = True
    if set_trainable:
        layer.trainable = True
    else:
        layer.trainable = False

vgg16_model2 = keras.applications.vgg16.VGG16()

input_layer2 = vgg16_model2.input
vgg16_model2.get_layer(index = 0).name = 'input2'

# Remove layers from block4_pool layer
last_layer2 = vgg16_model2.get_layer('block4_pool').output

# Adding layers
x = Conv2D(512, (3, 3), activation='relu', name='block5_conv1', padding='same')(last_layer2)
x = BatchNormalization(name='bn1')(x)
x = Conv2D(512, (3, 3), activation='relu', name='block5_conv2', padding='same')(x)
x = BatchNormalization(name='bn2')(x)
x = Conv2D(512, (3, 3), activation='relu', name='block5_conv3', padding='same')(x)
x = BatchNormalization(name='bn3')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name = 'block5_pool')(x)
x = Flatten(name = 'flatten')(x)
x = Dense(2048, activation='relu', name='fc1')(x)
x = BatchNormalization(name='bn4')(x)
fc22 = Dense(2048, activation='relu', name='fc2' )(x)
bn25 = BatchNormalization(name='bn5')(fc22)
out2 = Dropout(0.3, name='dropout1')(bn25)

#Classification layer
output_layer2 = Dense(106, activation='softmax', name='prediction2')(out2) 
model2 = Model(input_layer2, output_layer2)

#Train the last block
model2.trainable = True
set_trainable = False
for layer in model2.layers:
    if layer.name == 'block5_conv1':
        set_trainable = True
    if set_trainable:
        layer.trainable = True
    else:
        layer.trainable = False

con = concatenate([out1, out2])  # merge the outputs of the two models
output_layer3 = Dense(no_classes, activation='softmax', name='prediction3')(con)
multimodal_model1 = Model(inputs=[input_layer1, input_layer2], outputs=[output_layer3])

I tested model1 and model2, and I got good results. But when I tried to merge the two models the error appear. The problem initiated here:

multimodal_model1 = Model(inputs=[input_layer1, input_layer2], outputs=[output_layer3])

Please help to solve this problem.

Improve this question
$\endgroup$

1 Answer 1

Reset to default
-1
$\begingroup$

The problem is, you are trying to instantiate two VGG16 models at the same time and its confusing for the kernel to figure out which graph it needs to use. Atleast that is the speculation I have, because of the problems faced when trying to load multiple models in keras with tensorflow backend, its not straight forward.

Try commenting the code from when you are instantiating the second model and this error should go away.

Improve this answer
$\endgroup$
5
  • $\begingroup$ Thank you for reply. I tested model1 and model2, and I got good results. But when I tried to merge the two models the problem appeared. The problem initiated here: multimodal_model1 = Model(inputs=[input_layer1, input_layer2], outputs=[output_layer3]) $\endgroup$
    – Noran
    Nov 5, 2018 at 16:38
  • $\begingroup$ I dont think you can merge models like that, its better for you to create a model using Keras functional API and connecting the dots. I too faced issues when combining models out of the box. Also, why are you trying to ensemble models? $\endgroup$
    – Nischal Hp
    Nov 5, 2018 at 16:41
  • $\begingroup$ I created the model using functional API. Could you please explain what do you mean by connecting the dots? I have two datasets of images (type1 and type2), The model1 classifies the data in the first dataset and model2 classifies the data in the second dataset I want to connect the features from the first model and the features from the second model to create another model that make classification based on images (type1, type2). $\endgroup$
    – Noran
    Nov 5, 2018 at 16:53
  • $\begingroup$ Do you have examples of combining models? $\endgroup$
    – Noran
    Nov 5, 2018 at 16:55
  • 1
    $\begingroup$ you should do something like this : if data is type 1 use model1 else use model2. if you want a model that predict both data, you have to make a dataset with both and retrain the model from scratch (or maybe use fine tuning, why not) + maybe you should make another question on the website as it is a new one :) $\endgroup$
    – Jérémy Blain
    Nov 6, 2018 at 8:20

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.