python - 我在使用 Tensorflow 2.0 运行 RNN LSTM 模型时遇到错误

Question

几个月前我安装了tensorflow 2.0。我成功地运行了 CNN、线性回归和其他 keras 模型。我最近正在从 tensorflow 2.0 RNN with keras tutorials 学习 RNN。我从教程中运行了以下代码:

import collections
import matplotlib.pyplot as plt
import numpy as np

import tensorflow as tf

from tensorflow.keras import layers
batch_size = 64
input_dim = 28
units = 64
output_size = 10

def build_model(allow_cudnn_kernel=True):
  if allow_cudnn_kernel:
    lstm_layer = tf.keras.layers.LSTM(units, input_shape=(None, input_dim))
  else:
    lstm_layer = tf.keras.layers.RNN(
        tf.keras.layers.LSTMCell(units),
        input_shape=(None, input_dim))
  model = tf.keras.models.Sequential([
      lstm_layer,
      tf.keras.layers.BatchNormalization(),
      tf.keras.layers.Dense(output_size, activation='softmax')]
  )
  return model

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
sample, sample_label = x_train[0], y_train[0]
model = build_model(allow_cudnn_kernel=True)

model.compile(loss='sparse_categorical_crossentropy', 
              optimizer='sgd',
              metrics=['accuracy'])
model.fit(x_train, y_train,
          validation_data=(x_test, y_test),
          batch_size=batch_size,
          epochs=5)

这是我得到的输出:

Train on 60000 samples, validate on 10000 samples
Epoch 1/5
   64/60000 [..............................] - ETA: 1:17:13
---------------------------------------------------------------------------
UnknownError                              Traceback (most recent call last)
<ipython-input-8-6a1ac7233ae1> in <module>()
     31           validation_data=(x_test, y_test),
     32           batch_size=batch_size,
---> 33           epochs=5)

~\AppData\Roaming\Python\Python35\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,

~\AppData\Roaming\Python\Python35\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 

~\AppData\Roaming\Python\Python35\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?

~\AppData\Roaming\Python\Python35\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

~\AppData\Roaming\Python\Python35\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()

~\AppData\Roaming\Python\Python35\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
    518         # Lifting succeeded, so variables are initialized and we can run the
    519         # stateless function.
--> 520         return self._stateless_fn(*args, **kwds)
    521     else:
    522       canon_args, canon_kwds = \

~\AppData\Roaming\Python\Python35\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

~\AppData\Roaming\Python\Python35\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):

~\AppData\Roaming\Python\Python35\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()

~\AppData\Roaming\Python\Python35\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(

~\AppData\Roaming\Python\Python35\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\gokul adethya\appdata\local\programs\python\python35\lib\site-packages\six.py in raise_from(value, from_value)

UnknownError:  [_Derived_]  Fail to find the dnn implementation.
     [[{{node CudnnRNN}}]]
     [[sequential_1/lstm_1/StatefulPartitionedCall]] [Op:__inference_distributed_function_6815]

Function call stack:
distributed_function -> distributed_function -> distributed_function

我研究了该错误并发现了 this 。我尝试将 Growth 设置为 true，但我实际上并不了解它是如何工作的，但我仍然通过插入 https://www.tensorflow.org/guide/gpu 中的代码进行尝试，这仍然导致相同的错误。

配置:

tensorflow-gpu 版本 -- 2.0.0CUDA版本-v10.0

Answer 1

我终于找到了问题。问题是我的Cudnn低于tensorflow推荐的版本，即> = 7.4.1。当我升级到最新发布的版本时，它已修复