How to concatenate keras layers beyond the last axis

Question

I tried to concatenate keras layers beyond the last axis.

concat_layer = keras.layers.concatenate([layer1,layer2],axis=3);

The shapes of layer1 and layer2 are both (?,7,7),for now I want it become (?,7,7,2) rather than (?,7,14). If I wrote like axis=3, it returns "IndexError: list assignment index out of range"...

What should I do? Thank you so much!

Answer 1

Keras backend has an expand_dim operation, which you can you use with the Lambda layer. Try:

import keras.backend as K
from keras.layers import Lambda, concatenate

layer1 = Lambda(lambda x: K.expand_dims(x, axis=3))(layer1)
layer2 = Lambda(lambda x: K.expand_dims(x, axis=3))(layer2)
concat_layer = concatenate([layer1, layer2], axis=3)