LSTM编码器-解码器推理模型

Question

许多基于LSTM的seq2seq编解码结构的教程(例如英、法翻译)将模型定义如下：

encoder_inputs = Input(shape=(None,))
en_x=  Embedding(num_encoder_tokens, embedding_size)(encoder_inputs)

# Encoder lstm
encoder = LSTM(50, return_state=True)
encoder_outputs, state_h, state_c = encoder(en_x)

# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]

# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None,))

# french word embeddings
dex=  Embedding(num_decoder_tokens, embedding_size)
final_dex= dex(decoder_inputs)

# decoder lstm
decoder_lstm = LSTM(50, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(final_dex,
                                     initial_state=encoder_states)

decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)

# While training, model takes eng and french words and outputs #translated french word
fullmodel = Model([encoder_inputs, decoder_inputs], decoder_outputs)

# rmsprop is preferred for nlp tasks
fullmodel.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['acc'])

fullmodel.fit([encoder_input_data, decoder_input_data], decoder_target_data,
          batch_size=128,
          epochs=100,
          validation_split=0.20)

然后，为了进行预测，他们将推断模型定义如下：

# define the encoder model 
encoder_model = Model(encoder_inputs, encoder_states)
encoder_model.summary()


# Redefine the decoder model with decoder will be getting below inputs from encoder while in prediction
decoder_state_input_h = Input(shape=(50,))
decoder_state_input_c = Input(shape=(50,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
final_dex2= dex(decoder_inputs)

decoder_outputs2, state_h2, state_c2 = decoder_lstm(final_dex2, initial_state=decoder_states_inputs)

decoder_states2 = [state_h2, state_c2]
decoder_outputs2 = decoder_dense(decoder_outputs2)

# sampling model will take encoder states and decoder_input(seed initially) and output the predictions(french word index) We dont care about decoder_states2
decoder_model = Model(
    [decoder_inputs] + decoder_states_inputs,
    [decoder_outputs2] + decoder_states2)

然后使用以下方法进行预测：

# Reverse-lookup token index to decode sequences back to
# something readable.
reverse_input_char_index = dict(
    (i, char) for char, i in input_token_index.items())
reverse_target_char_index = dict(
    (i, char) for char, i in target_token_index.items())


def decode_sequence(input_seq):
    # Encode the input as state vectors.
    states_value = encoder_model.predict(input_seq)

    # Generate empty target sequence of length 1.
    target_seq = np.zeros((1,1))
    # Populate the first character of target sequence with the start character.
    target_seq[0, 0] = target_token_index['START_']

   # Sampling loop for a batch of sequences
    # (to simplify, here we assume a batch of size 1).
    stop_condition = False
    decoded_sentence = ''
    while not stop_condition:
        output_tokens, h, c = decoder_model.predict(
            [target_seq] + states_value)

        # Sample a token
        sampled_token_index = np.argmax(output_tokens[0, -1, :])
        sampled_char = reverse_target_char_index[sampled_token_index]
        decoded_sentence += ' '+sampled_char

        # Exit condition: either hit max length
        # or find stop character.
        if (sampled_char == '_END' or
           len(decoded_sentence) > 52):
            stop_condition = True

       # Update the target sequence (of length 1).
        target_seq = np.zeros((1,1))
        target_seq[0, 0] = sampled_token_index

        # Update states
        states_value = [h, c]
return decoded_sentence

我的问题是，他们用“全模特”这个名字训练模特来获得最好的体重.在预测部分，他们使用了具有名称的推理模型(encoder_model & decoder_model)。所以他们没有使用“全模型”的任何重量?！

我不明白他们怎么会从受过训练的模特身上受益！

Answer 1

诀窍是，所有的变量都在同一个变量范围内，因此这些变量被重用。

Answer 2

如果您注意到，经过训练的层重将被重用。例如，在创建decoder_model时，我们使用定义为完整模型的一部分的decoder_lstm层，decoder_outputs2，state_h2，state_c2 = decoder_lstm(final_dex2，initial_state=decoder_states_inputs)，

而编码器模型也采用了以前定义的encoder_inputs层和encoder_states层。encoder_model =模型(encoder_inputs，encoder_states)

由于编解码模型的体系结构，我们需要执行这些实现方案.此外，正如keras文档所提到的，使用functional，可以很容易地重用经过训练的模型:通过在张量上调用模型，您可以将任何模型视为一个层。注意，通过调用模型，您不仅重用了模型的体系结构，还重用了它的权重。有关详细信息，请参阅- https://keras.io/getting-started/functional-api-guide/#all-models-are-callable-just-like-layers