我正在尝试构建用于序列建模和神经嵌入的单向RNN。我建立了一个自定义类，以尝试各种体系结构和参数。代码中的数据管理器类是另一类，主要用于读取文本数据，对其进行处理并将其转换为数字向量。 tf_train_set是tensorSliceDataset，其中包含数字矢量和数据集的60％的标签。其余40％位于tf_valid_set中。
我的RNN具有以下代码：
class UniRNN:
def __init__(self, cell_type= 'gru', embed_size= 128, state_sizes= [128, 64], data_manager= None):
self.cell_type = cell_type
self.state_sizes = state_sizes
self.embed_size = embed_size
self.data_manager = data_manager
self.vocab_size = self.data_manager.vocab_size +1
#return the correspoding memory cell
@staticmethod
def get_layer(cell_type= 'gru', state_size= 128, return_sequences= False, activation = 'tanh'):
if cell_type=='gru':
return tf.keras.layers.GRU(state_size, return_sequences=return_sequences, activation=activation)
elif cell_type== 'lstm':
return tf.keras.layers.LSTM(state_size, return_sequences=return_sequences, activation=activation)
else:
return tf.keras.layers.SimpleRNN(state_size, return_sequences=return_sequences, activation=activation)
def build(self):
x = tf.keras.layers.Input(shape=[None])
h = tf.keras.layers.Embedding(self.vocab_size, self.embed_size, mask_zero=True, trainable=True)(x)
num_layers = len(self.state_sizes)
for i in range(num_layers):
h = self.get_layer(self.cell_type, self.state_sizes[i], return_sequences=True)(h)
h = tf.keras.layers.Dense(dm.num_classes, activation='softmax')(h)
self.model = tf.keras.Model(inputs=x, outputs=h)
def compile_model(self, *args, **kwargs):
self.model.compile(*args, **kwargs)
def fit(self, *args, **kwargs):
return self.model.fit(*args, **kwargs)
def evaluate(self, *args, **kwargs):
self.model.evaluate(*args, **kwargs)
要拟合模型，我的代码是：
uni_rnn = UniRNN(cell_type='basic_rnn', embed_size=128, state_sizes=[128, 128], data_manager=dm) #Insert your code here
uni_rnn.build()
# uni_rnn.model.summary()
opt = tf.keras.optimizers.RMSprop(learning_rate=0.001)
uni_rnn.compile_model(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=['accuracy'])
uni_rnn.fit(dm.tf_train_set.batch(64), epochs=20, validation_data = dm.tf_valid_set.batch(64))
运行此代码时，出现以下错误：
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-184-abef9ae0cbcd> in <module>
3 opt = tf.keras.optimizers.RMSprop(learning_rate=0.001)
4 uni_rnn.compile_model(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=['accuracy'])
----> 5 uni_rnn.fit(dm.tf_train_set.batch(64), epochs=20, validation_data = dm.tf_valid_set.batch(64))
<ipython-input-170-53f4c12769ab> in fit(self, *args, **kwargs)
31
32 def fit(self, *args, **kwargs):
---> 33 return self.model.fit(*args, **kwargs)
34
35 def evaluate(self, *args, **kwargs):
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\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, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
817 max_queue_size=max_queue_size,
818 workers=workers,
--> 819 use_multiprocessing=use_multiprocessing)
820
821 def evaluate(self,
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
340 mode=ModeKeys.TRAIN,
341 training_context=training_context,
--> 342 total_epochs=epochs)
343 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
344
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
126 step=step, mode=mode, size=current_batch_size) as batch_logs:
127 try:
--> 128 batch_outs = execution_function(iterator)
129 except (StopIteration, errors.OutOfRangeError):
130 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in execution_function(input_fn)
96 # `numpy` translates Tensors to values in Eager mode.
97 return nest.map_structure(_non_none_constant_value,
---> 98 distributed_function(input_fn))
99
100 return execution_function
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\eager\def_function.py in __call__(self, *args, **kwds)
566 xla_context.Exit()
567 else:
--> 568 result = self._call(*args, **kwds)
569
570 if tracing_count == self._get_tracing_count():
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
630 # Lifting succeeded, so variables are initialized and we can run the
631 # stateless function.
--> 632 return self._stateless_fn(*args, **kwds)
633 else:
634 canon_args, canon_kwds = \
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\eager\function.py in __call__(self, *args, **kwargs)
2361 with self._lock:
2362 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
-> 2363 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2364
2365 @property
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\eager\function.py in _filtered_call(self, args, kwargs)
1609 if isinstance(t, (ops.Tensor,
1610 resource_variable_ops.BaseResourceVariable))),
-> 1611 self.captured_inputs)
1612
1613 def _call_flat(self, args, captured_inputs, cancellation_manager=None):
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1690 # No tape is watching; skip to running the function.
1691 return self._build_call_outputs(self._inference_function.call(
-> 1692 ctx, args, cancellation_manager=cancellation_manager))
1693 forward_backward = self._select_forward_and_backward_functions(
1694 args,
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\eager\function.py in call(self, ctx, args, cancellation_manager)
543 inputs=args,
544 attrs=("executor_type", executor_type, "config_proto", config),
--> 545 ctx=ctx)
546 else:
547 outputs = execute.execute_with_cancellation(
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\tensorflow_core\python\eager\execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
65 else:
66 message = e.message
---> 67 six.raise_from(core._status_to_exception(e.code, message), None)
68 except TypeError as e:
69 keras_symbolic_tensors = [
~\anaconda3\envs\myenv_tf21_p37\lib\site-packages\six.py in raise_from(value, from_value)
InvalidArgumentError: assertion failed: [Condition x == y did not hold element-wise:] [x (loss/dense_13_loss/SparseSoftmaxCrossEntropyWithLogits/Shape_1:0) = ] [64 1] [y (loss/dense_13_loss/SparseSoftmaxCrossEntropyWithLogits/strided_slice:0) = ] [64 100]
[[node loss/dense_13_loss/SparseSoftmaxCrossEntropyWithLogits/assert_equal_1/Assert/Assert (defined at <ipython-input-170-53f4c12769ab>:33) ]] [Op:__inference_distributed_function_111597]
Function call stack:
distributed_function
有人可以解释一下问题是什么吗？也许我该如何解决？
答案 0 :(得分：1)
循环中的最后一个RNN必须具有return_sequence = False。为此，您可以简单地做到：
def build(self):
x = tf.keras.layers.Input(shape=[None])
h = tf.keras.layers.Embedding(self.vocab_size, self.embed_size,
mask_zero=True, trainable=True)(x)
num_layers = len(self.state_sizes)
for i in range(num_layers-1):
h = self.get_layer(self.cell_type, self.state_sizes[i], return_sequences=True)(h)
h = self.get_layer(self.cell_type, self.state_sizes[i], return_sequences=False)(h)
h = tf.keras.layers.Dense(dm.num_classes, activation='softmax')(h)
self.model = tf.keras.Model(inputs=x, outputs=h)