Question

当前正在使用tf2.0处理回归问题。为了准备我的数据集，我使用了以下代码：

train = tf.data.Dataset.from_tensor_slices(([train_X], [train_y])).batch(BATCH_SIZE).repeat()
val = tf.data.Dataset.from_tensor_slices(([val_X], [val_y])).batch(BATCH_SIZE).repeat()

现在，如果我们看看它们的形状：

<RepeatDataset shapes: ((None, 42315, 20), (None, 42315)), types: (tf.float64, tf.float64)>
<RepeatDataset shapes: ((None, 2228, 20), (None, 2228)), types: (tf.float64, tf.float64)>

我认为这是正确的。现在，如果我通过如下所示的模型运行它们，它们似乎可以很好地训练和工作：

simple_lstm_model = tf.keras.models.Sequential([
    tf.keras.layers.LSTM(8),
    tf.keras.layers.Dense(1)
])

simple_lstm_model.compile(optimizer='adam', loss='mae')

history = simple_lstm_model.fit(train, epochs=EPOCHS,
                      steps_per_epoch=EVALUATION_INTERVAL,
                      validation_data=val, validation_steps=50)

但是，当我使模型稍微复杂一些并尝试对其进行编译时，它给了我这个问题的标题错误。有关错误的详细信息位于此问题的最底部。复杂的模型如下所示：

comp_lstm = tf.keras.models.Sequential([
    tf.keras.layers.LSTM(64),
    tf.keras.layers.LSTM(64),
    tf.keras.layers.LSTM(64),
    tf.keras.layers.Dense(1)
])

comp_lstm.compile(optimizer='adam', loss='mae')

history = comp_lstm.fit(train, 
                      epochs=EPOCHS,
                      steps_per_epoch=EVALUATION_INTERVAL,
                      validation_data=val, validation_steps=50)

实际上，我想尝试双向LSTM，但似乎LSTM的多个堆栈本身给了我以下所述的问题。

错误

TypeError                                 Traceback (most recent call last)
<ipython-input-21-8a86aab8a730> in <module>
      2 EPOCHS = 20
      3 
----> 4 history = comp_lstm.fit(train, 
      5                       epochs=EPOCHS,
      6                       steps_per_epoch=EVALUATION_INTERVAL,

~/python_envs/p2/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
     64   def _method_wrapper(self, *args, **kwargs):
     65     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
---> 66       return method(self, *args, **kwargs)
     67 
     68     # Running inside `run_distribute_coordinator` already.

~/python_envs/p2/lib/python3.8/site-packages/tensorflow/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_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
    846                 batch_size=batch_size):
    847               callbacks.on_train_batch_begin(step)
--> 848               tmp_logs = train_function(iterator)
    849               # Catch OutOfRangeError for Datasets of unknown size.
    850               # This blocks until the batch has finished executing.

~/python_envs/p2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    578         xla_context.Exit()
    579     else:
--> 580       result = self._call(*args, **kwds)
    581 
    582     if tracing_count == self._get_tracing_count():

~/python_envs/p2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    609       # In this case we have created variables on the first call, so we run the
    610       # defunned version which is guaranteed to never create variables.
--> 611       return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
    612     elif self._stateful_fn is not None:
    613       # Release the lock early so that multiple threads can perform the call

TypeError: 'NoneType' object is not callable

Answer 1

问题在于，当您堆叠多个LSTM时，我们应该在LSTM层中使用参数return_sequences = True。

这是因为如果return_sequences = False（默认行为），LSTM将返回Output of the Last Time Step。但是，当我们堆叠LSTM时，将需要Output中的Complete Sequence，而不仅仅是最后一个Time Step。

将模型更改为

comp_lstm = tf.keras.models.Sequential([
    tf.keras.layers.LSTM(64, return_sequences = True),
    tf.keras.layers.LSTM(64, return_sequences = True),
    tf.keras.layers.LSTM(64),
    tf.keras.layers.Dense(1)
])

应解决该错误。

这样，您也可以使用Bi-Directional LSTMs。

如果您遇到任何其他错误，请告诉我，我们将竭诚为您服务。

希望这会有所帮助。学习愉快！

TypeError：'NoneType'对象不可调用Tensorflow

错误

1 个答案: