CODEWITHSUNDEEP
tensorflowkerastf.keraskeras-layer
deijany91
deijany91

Reputation: 19

How to combine two keras models (one frozen), using functional API

How to combine two Keras models using functional API. I mean, I have two models (a, which is pretrained with freezer weights, and b). I want to create a c model by adding the b model to the bottom of the frozen model.

In detail, I have the following two models:

def define_neural_network_model_1st(input_shape, initializer, outputs = 1):
   ........
  return model

model a

def define_neural_network_model_2st(input_shape, initializer, outputs = 1):
   ........
  return model

model2

Since the first one is trained I am loading the weights and freezing the model.

   neural_network_model_1st.load_weights('./../some_path.hdf5')
   neural_network_model_1st.trainable = False

When I am trying to merge both blocks in the following way

   merge_interpretation = Model(inputs=[neural_network_model_1st.inputs], outputs=neural_network_model_2st(neural_network_model_1st.inputs))

I am receiving:

result

What I am doing wrong? I am waiting to have 1 layer from the frozen model plus all layers in the second one.

Upvotes: 0

Views: 533

Answers (1)

Mohammad Ahmed
Mohammad Ahmed

Reputation: 1634

Let suppose I have two models,

resnet_50 = tf.keras.applications.ResNet50(weights=None,
                           input_shape=(224 , 224 , 3),
                           classes = 2)
vgg_16 = tf.keras.applications.VGG16(
weights=None,
input_shape=(224,224,3),
classes=2,
include_top=False)

Now I want to merge these two models, first of all, I will make sure the output of the first model should be the same shape as the input of the second model, so for that first I have to do some pre-processing.

model = tf.keras.Model(vgg_16.inputs , vgg_16.layers[-2].output)
model2 = tf.keras.Model(resnet_50.get_layer('conv4_block6_out').input , resnet_50.output)
input = tf.keras.layers.Input(shape=(224 , 224 , 3))
out1 = model(input)
intermediate_layer = tf.keras.layers.Conv2D(model2.inputs[0][0].shape[2] , 1 , 1 , padding='same')(out1)
out2 = model2(intermediate_layer)
f_model = tf.keras.Model(input , out2)
tf.keras.utils.plot_model(
f_model,
show_shapes=True)

Now this is the output shape of the two models [The Architecture of the combined two models][1] [1]: https://i.sstatic.net/F7H8d.png

You can see the individual summary of the models by doing this

f_model.layers[1].summary() #This will show the summary of the first model VGG16
f_model.layers[3].summary() #This will show the summary of the second model Resnet18

But if you run the f_model.summary() this will not show the summary of the combined two models as one, because in the backend Keras take model one as a functional graph Node so it acts as a Node of the graph.

Upvotes: 1

Related Questions