我想使用这个模型，但我们不能再使用merge函数了。

image_model = Sequential([    Dense(embedding_size, input_shape=(2048,), activation='relu'),    RepeatVector(max_len)])caption_model = Sequential([    Embedding(vocab_size, embedding_size, input_length=max_len),    LSTM(256, return_sequences=True),    TimeDistributed(Dense(300))])final_model = Sequential([    Merge([image_model, caption_model], mode='concat', concat_axis=1),    Bidirectional(LSTM(256, return_sequences=False)),    Dense(vocab_size),    Activation('softmax')])

我按照以下方式重写了它，排除了final_model:

image_in = Input(shape=(2048,))caption_in = Input(shape=(max_len, vocab_size))merged = concatenate([image_model(image_in), caption_model(caption_in)],axis=0)latent = Bidirectional(LSTM(256, return_sequences=False))(merged)out = Dense(vocab_size, activation='softmax')(latent)final_model = Model([image_in, caption_in], out)final_model.compile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy'])final_model.summary()

这也让我得到了:

ValueError: "input_length" is 40, but received input has shape (None, 40, 8256).

有谁能帮我修复这个问题吗？来源:https://github.com/yashk2810/Image-Captioning/blob/master/Image%20Captioning%20InceptionV3.ipynb

回答：

你应该将caption_in定义为二维: Input(shape=(max_len,))。在你的情况下，拼接操作必须在最后一个轴上进行: axis=-1。其余部分看起来没问题

embedding_size=300max_len=40vocab_size=8256image_model = Sequential([    Dense(embedding_size, input_shape=(2048,), activation='relu'),    RepeatVector(max_len)])caption_model = Sequential([    Embedding(vocab_size, embedding_size, input_length=max_len),    LSTM(256, return_sequences=True),    TimeDistributed(Dense(300))])image_in = Input(shape=(2048,))caption_in = Input(shape=(max_len,))merged = concatenate([image_model(image_in), caption_model(caption_in)],axis=-1)latent = Bidirectional(LSTM(256, return_sequences=False))(merged)out = Dense(vocab_size, activation='softmax')(latent)final_model = Model([image_in, caption_in], out)final_model.compile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy'])final_model.summary()