How to correctly concatenate a Flatten layer and a feature vector in Keras

Question

I just need to concatenate a flatten layer and a feature vector in Keras. This is the code:

#custom parameters
n_features = 38

vgg_model = VGGFace(include_top=False, input_shape=(224, 224, 3))
last_layer = vgg_model.get_layer('pool5').output

x = Flatten(name='flatten')(last_layer)

# feature vector
feature_vector = Input(shape = (n_features,))

conc = concatenate(([x, feature_vector]), axis=1)


layer_intermediate = Dense(128, activation='relu', name='fc6')(conc)
layer_intermediate1 = Dense(32, activation='relu', name='fc7')(layer_intermediate)
out = Dense(5, activation='softmax', name='fc8')(layer_intermediate1)

custom_vgg_model = Model(vgg_model.input, out)

But I'm getting this error:

---> 20 custom_vgg_model = Model(vgg_model.input, out)

ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_88:0", shape=(?, 38), dtype=float32) at layer "input_88". The following previous layers were accessed without issue: ['input_87', 'conv1_1', 'conv1_2', 'pool1', 'conv2_1', 'conv2_2', 'pool2', 'conv3_1', 'conv3_2', 'conv3_3', 'pool3', 'conv4_1', 'conv4_2', 'conv4_3', 'pool4', 'conv5_1', 'conv5_2', 'conv5_3', 'pool5', 'flatten']

Btw the shape of the flatten layer is (None, 25088)

zihaozhihao zihaozhihao · Accepted Answer · 2019-09-28T23:20:46

Since your feature_vector is also Input. Try to add feature_vector into inputs when you define the Model.

custom_vgg_model = Model([vgg_model.input,feature_vector], out)

How to correctly concatenate a Flatten layer and a feature vector in Keras

1 Answers