SceneDesc.py 文件源码

def create_model(self, ret_model = False):

        image_model = Sequential()
        image_model.add(Dense(EMBEDDING_DIM, input_dim = 4096, activation='relu'))
        image_model.add(RepeatVector(self.max_length))

        lang_model = Sequential()
        lang_model.add(Embedding(self.vocab_size, 256, input_length=self.max_length))
        lang_model.add(LSTM(256,return_sequences=True))
        lang_model.add(TimeDistributed(Dense(EMBEDDING_DIM)))

        model = Sequential()
        model.add(Merge([image_model, lang_model], mode='concat'))
        model.add(LSTM(1000,return_sequences=False))
        model.add(Dense(self.vocab_size))
        model.add(Activation('softmax'))

        print ("Model created!")

        if(ret_model==True):
            return model

        model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
        return model