如何从Chollet教程修复RNN无效参数错误

Question

我正在尝试在LSTM网络上尝试本教程。代码如下：

from keras.models import Model
from keras import layers
from keras import Input

text_vocabulary_size = 10000
question_vocabulary_size = 10000
answer_vocabulary_size = 500

# Our text input is a variable-length sequence of integers.
# Note that we can optionally name our inputs!
text_input = Input(shape=(None,), dtype='int32', name='text')

# Which we embed into a sequence of vectors of size 64
embedded_text = layers.Embedding(64, text_vocabulary_size)(text_input)

# Which we encoded in a single vector via a LSTM
encoded_text = layers.LSTM(32)(embedded_text)

# Same process (with different layer instances) for the question
question_input = Input(shape=(None,), dtype='int32', name='question')
embedded_question = layers.Embedding(32, question_vocabulary_size)(question_input)
encoded_question = layers.LSTM(16)(embedded_question)

# We then concatenate the encoded question and encoded text
concatenated = layers.concatenate([encoded_text, encoded_question], axis=-1)

# And we add a softmax classifier on top
answer = layers.Dense(answer_vocabulary_size, activation='softmax')(concatenated)

# At model instantiation, we specify the two inputs and the output:
model = Model([text_input, question_input], answer)
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['acc'])

num_samples = 1000
max_length = 100

text = np.random.randint(1, text_vocabulary_size,
                        size=(num_samples, max_length))
question = np.random.randint(1, question_vocabulary_size,
                             size=(num_samples, max_length))

answers = np.random.randint(0, 1, 
                           size=(num_samples, answer_vocabulary_size))

model.fit([text, question], answers, epochs=10, batch_size=128)

但是，出现以下错误

---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-115-097c6009c2d2> in <module>()
     45                            size=(num_samples, answer_vocabulary_size))
     46 
---> 47 model.fit([text, question], answers, epochs=10, batch_size=128)

C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
   1037                                         initial_epoch=initial_epoch,
   1038                                         steps_per_epoch=steps_per_epoch,
-> 1039                                         validation_steps=validation_steps)
   1040 
   1041     def evaluate(self, x=None, y=None,

C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training_arrays.py in fit_loop(model, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
    197                     ins_batch[i] = ins_batch[i].toarray()
    198 
--> 199                 outs = f(ins_batch)
    200                 outs = to_list(outs)
    201                 for l, o in zip(out_labels, outs):

C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py in __call__(self, inputs)
   2713                 return self._legacy_call(inputs)
   2714 
-> 2715             return self._call(inputs)
   2716         else:
   2717             if py_any(is_tensor(x) for x in inputs):

C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py in _call(self, inputs)
   2673             fetched = self._callable_fn(*array_vals, run_metadata=self.run_metadata)
   2674         else:
-> 2675             fetched = self._callable_fn(*array_vals)
   2676         return fetched[:len(self.outputs)]
   2677 

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in __call__(self, *args, **kwargs)
   1437           ret = tf_session.TF_SessionRunCallable(
   1438               self._session._session, self._handle, args, status,
-> 1439               run_metadata_ptr)
   1440         if run_metadata:
   1441           proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
    526             None, None,
    527             compat.as_text(c_api.TF_Message(self.status.status)),
--> 528             c_api.TF_GetCode(self.status.status))
    529     # Delete the underlying status object from memory otherwise it stays alive
    530     # as there is a reference to status from this from the traceback due to

InvalidArgumentError: indices[56,0] = 7134 is not in [0, 32)
     [[{{node embedding_18/embedding_lookup}}]]

我不明白错误在说什么，也不知道如何解决。

从我阅读的内容中，我认为这意味着我的输入没有正确的尺寸，但实际上并没有弄错什么。我完全按照Francois Challot在第239-240页上的《用Python深度学习》编写的代码进行了复制。因此它应该运行。我正在尝试使用它来理解RNN的工作原理，并更好地了解代码机制，因此，修复此问题的任何帮助都将是很棒的。

注意，我从这个问题中保留的代码中的一些注释： How LSTM deal with variable length sequence

这是model.summary()的印刷品