我在 text_classification_rnn 的 Google tensorflow2.0 教程中遇到了一个令人惊讶的错误

Question

When i reading Google tensorflow2.0 tutorials, i meet an surprised error when i try to test in my jupyter. It is so strange！It run fluently in Google colab! The tutorials is this My computer GPU is gtx1060 6G, and memory is 16G, I think my computer is ok to run this tutorials.

I try run it on Jupyter, and it run error.But run fluently on Google colab!

You can see the error code following or go to the web :

from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

import tensorflow_datasets as tfds
# tfds.disable_progress_bar()
(train_data, test_data), info = tfds.load(
    'imdb_reviews/subwords8k', 
    split = (tfds.Split.TRAIN, tfds.Split.TEST), 
    with_info=True, as_supervised=True)
encoder = info.features['text'].encoder
padded_shapes = ([None],())
train_batches = train_data.shuffle(1000).padded_batch(10, padded_shapes = padded_shapes)
test_batches = test_data.shuffle(1000).padded_batch(10, padded_shapes = padded_shapes)

embedding_dim=16

model = keras.Sequential([
    layers.Embedding(encoder.vocab_size, embedding_dim,mask_zero=True),
    layers.Bidirectional(tf.keras.layers.LSTM(32)),
    layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])

history = model.fit(
    train_batches,
    epochs=10,
    validation_data=test_batches, validation_steps=20,verbose=2)

It is my first time meeting this error, and I don't know how to fix it, but it run fluently on Google colab, I don't know why? The error following:

Epoch 1/10
---------------------------------------------------------------------------
CancelledError                            Traceback (most recent call last)
<ipython-input-2-8f27353fef79> in <module>
     31     train_batches,
     32     epochs=10,
---> 33     validation_data=test_batches, validation_steps=20,verbose=2)

c:\users\sha\anaconda3\envs\tensorflow2\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)
    726         max_queue_size=max_queue_size,
    727         workers=workers,
--> 728         use_multiprocessing=use_multiprocessing)
    729 
    730   def evaluate(self,

c:\users\sha\anaconda3\envs\tensorflow2\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, **kwargs)
    322                 mode=ModeKeys.TRAIN,
    323                 training_context=training_context,
--> 324                 total_epochs=epochs)
    325             cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
    326 

c:\users\sha\anaconda3\envs\tensorflow2\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)
    121         step=step, mode=mode, size=current_batch_size) as batch_logs:
    122       try:
--> 123         batch_outs = execution_function(iterator)
    124       except (StopIteration, errors.OutOfRangeError):
    125         # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in execution_function(input_fn)
     84     # `numpy` translates Tensors to values in Eager mode.
     85     return nest.map_structure(_non_none_constant_value,
---> 86                               distributed_function(input_fn))
     87 
     88   return execution_function

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\tensorflow_core\python\eager\def_function.py in __call__(self, *args, **kwds)
    455 
    456     tracing_count = self._get_tracing_count()
--> 457     result = self._call(*args, **kwds)
    458     if tracing_count == self._get_tracing_count():
    459       self._call_counter.called_without_tracing()

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
    485       # In this case we have created variables on the first call, so we run the
    486       # defunned version which is guaranteed to never create variables.
--> 487       return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
    488     elif self._stateful_fn is not None:
    489       # Release the lock early so that multiple threads can perform the call

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\tensorflow_core\python\eager\function.py in __call__(self, *args, **kwargs)
   1821     """Calls a graph function specialized to the inputs."""
   1822     graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
-> 1823     return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
   1824 
   1825   @property

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\tensorflow_core\python\eager\function.py in _filtered_call(self, args, kwargs)
   1139          if isinstance(t, (ops.Tensor,
   1140                            resource_variable_ops.BaseResourceVariable))),
-> 1141         self.captured_inputs)
   1142 
   1143   def _call_flat(self, args, captured_inputs, cancellation_manager=None):

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\tensorflow_core\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
   1222     if executing_eagerly:
   1223       flat_outputs = forward_function.call(
-> 1224           ctx, args, cancellation_manager=cancellation_manager)
   1225     else:
   1226       gradient_name = self._delayed_rewrite_functions.register()

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\tensorflow_core\python\eager\function.py in call(self, ctx, args, cancellation_manager)
    509               inputs=args,
    510               attrs=("executor_type", executor_type, "config_proto", config),
--> 511               ctx=ctx)
    512         else:
    513           outputs = execute.execute_with_cancellation(

c:\users\sha\anaconda3\envs\tensorflow2\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 = [

c:\users\sha\anaconda3\envs\tensorflow2\lib\site-packages\six.py in raise_from(value, from_value)

CancelledError:  [_Derived_]RecvAsync is cancelled.
     [[{{node Reshape_11/_38}}]] [Op:__inference_distributed_function_16087]

Function call stack:
distributed_function

Thanks for anyone help me！

Answer 1

Try to reduce the batch_size, it should work.