我正在尝试在奖励部分->下列出的their blog上实现Keras单词级示例，如果我想对整数序列使用单词级模型怎么办？
我已经用名称标记了图层，以帮助以后将图层从已加载的模型重新连接到推理模型。我想我遵循了他们的示例模型：
# Define an input sequence and process it - where the shape is (timesteps, n_features)
encoder_inputs = Input(shape=(None, src_vocab), name='enc_inputs')
# Add an embedding layer to process the integer encoded words to give some 'sense' before the LSTM layer
encoder_embedding = Embedding(src_vocab, latent_dim, name='enc_embedding')(encoder_inputs)
# The return_state constructor argument configures a RNN layer to return a list where the first entry is the outputs
# and the next entries are the internal RNN states. This is used to recover the states of the encoder.
encoder_outputs, state_h, state_c = LSTM(latent_dim, return_state=True, name='encoder_lstm')(encoder_embedding)
# 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 of the RNN.
decoder_inputs = Input(shape=(None, target_vocab), name='dec_inputs')
decoder_embedding = Embedding(target_vocab, latent_dim, name='dec_embedding')(decoder_inputs)
# The return_sequences constructor argument, configuring a RNN to return its full sequence of outputs (instead of
# just the last output, which the defaults behavior).
decoder_lstm = LSTM(latent_dim, return_sequences=True, name='dec_lstm')(decoder_embedding, initial_state=encoder_states)
decoder_outputs = Dense(target_vocab, activation='softmax', name='dec_outputs')(decoder_lstm)
# Put the model together
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
但我明白了
ValueError: Input 0 is incompatible with layer encoder_lstm: expected ndim=3, found ndim=4
在线上
encoder_outputs, state_h, state_c = LSTM(...
我想念什么？还是博客上的示例假设我已跳过了某个步骤？
更新：
我正在接受以下培训：
X = [source_data, target_data]
y = offset_data(target_data)
model.fit(X, y, ...)
更新2：
所以，我还不在那里。我如上所述定义了
decoder_lstm和decoder_outputs并修复了输入。当我从h5文件加载模型并建立推理模型时，我尝试使用以下命令连接到训练modeldecoder_inputs = model.input[1] # dec_inputs (Input(shape=(None,)))
# decoder_embedding = model.layers[3] # dec_embedding (Embedding(target_vocab, latent_dim))
target_vocab = model.output_shape[2]
decoder_state_input_h = Input(shape=(latent_dim,), name='input_3') # named to avoid conflict
decoder_state_input_c = Input(shape=(latent_dim,), name='input_4')
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
# Use decoder_lstm from the training model
# decoder_lstm = LSTM(latent_dim, return_sequences=True)
decoder_lstm = model.layers[5] # dec_lstm
decoder_outputs, state_h, state_c = decoder_lstm(decoder_inputs, initial_state=decoder_states_inputs)
但我得到一个错误
ValueError: Input 0 is incompatible with layer dec_lstm: expected ndim=3, found ndim=2
尝试通过
decoder_embedding而不是decoder_inputs也会失败。我正在尝试改写lstm_seq2seq_restore.py的示例，但其中不包括嵌入层的复杂性。
更新3：
当我使用
decoder_outputs, state_h, state_c = decoder_lstm(decoder_embedding, ...)构建推理模型时，我已经确认decoder_embedding是Embedding类型的对象，但是得到：ValueError: Layer dec_lstm was called with an input that isn't a symbolic tensor. Received type: <class 'keras.layers.embeddings.Embedding'>. Full input: [<keras.layers.embeddings.Embedding object at 0x1a1f22eac8>, <tf.Tensor 'input_3:0' shape=(?, 256) dtype=float32>, <tf.Tensor 'input_4:0' shape=(?, 256) dtype=float32>]. All inputs to the layer should be tensors.
该模型的完整代码在Bitbucket上。
最佳答案
问题出在Input层的输入形状中。嵌入层接受整数序列作为输入，该整数序列对应于句子中的单词索引。由于此处句子中的单词数不是固定的，因此必须将Input图层的输入形状设置为(None,)。
我认为您会误以为我们的模型中没有嵌入层，因此模型的输入形状为(timesteps, n_features)以使其与LSTM层兼容。
更新：
您需要先将decoder_inputs传递给Embedding层，然后将生成的输出张量传递给decoder_lstm层，如下所示：
decoder_inputs = model.input[1] # (Input(shape=(None,)))
# pass the inputs to the embedding layer
decoder_embedding = model.get_layer(name='dec_embedding')(decoder_inputs)
# ...
decoder_lstm = model.get_layer(name='dec_lstm') # dec_lstm
decoder_outputs, state_h, state_c = decoder_lstm(decoder_embedding, ...)
更新2：
在培训期间，创建
decoder_lstm层时，需要设置return_state=True：decoder_lstm, _, _ = LSTM(latent_dim, return_sequences=True, return_state=True, name='dec_lstm')(decoder_embedding, initial_state=encoder_states)
关于python - 具有整数序列的Keras示例单词级模型给出了“预期ndim = 3，发现ndim = 4”，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/51829810/