fin_model.summary gives an error

[abhisingh192]

the Merge was deprecated so I'm using this

fin_model.add(Concatenate([image_model, lang_model]))
but when i try to get the summary of the fin_model I'm getting a ValueError. ValueError: This model has not yet been built. Build the model first by calling build() or calling fit() with some data. Or specify input_shape or batch_input_shape in the first layer for automatic build.
Anyone knows how to fix it?

[abhisingh192]

`
fin_model = Sequential()
fin_model = Concatenate()( [lang_model.output, image_model.output] )

fin_model = Dropout(0.5)(fin_model)
fin_model = BatchNormalization()(fin_model)
fin_model = Bidirectional(LSTM(1000,return_sequences=False))(fin_model)

fin_model = Dense(vocab_size)(fin_model)
fin_model = Activation('softmax')(fin_model)
fin_model = Model([lang_model.input, image_model.input],fin_model)
print ("Model created!")`

I also used this, but the problem with this is that the layers ordering does not match. Can anyone help with this. I want to get the fin_model

[IngaMD]

`
fin_model = Sequential()
fin_model = Concatenate()( [lang_model.output, image_model.output] )

fin_model = Dropout(0.5)(fin_model)
fin_model = BatchNormalization()(fin_model)
fin_model = Bidirectional(LSTM(1000,return_sequences=False))(fin_model)

fin_model = Dense(vocab_size)(fin_model)
fin_model = Activation('softmax')(fin_model)
fin_model = Model([lang_model.input, image_model.input],fin_model)
print ("Model created!")`

I also used this, but the problem with this is that the layers ordering does not match. Can anyone help with this. I want to get the fin_model

Hi! did you find a solution ? ... if yes please share, I need to try it out, thanks in advance!