python - 我的 tensorflow-gpu 安装不适用于 CNN

问题描述

这是我的代码：

model = Sequential()

# CONVOLUTIONAL LAYER
model.add(Conv2D(filters=32, kernel_size=(4,4),input_shape=(28, 28, 1), activation='relu',))
# POOLING LAYER
model.add(MaxPool2D(pool_size=(2, 2)))

# FLATTEN IMAGES FROM 28 by 28 to 764 BEFORE FINAL LAYER
model.add(Flatten())

# 128 NEURONS IN DENSE HIDDEN LAYER (YOU CAN CHANGE THIS NUMBER OF NEURONS)
model.add(Dense(128, activation='relu'))

# LAST LAYER IS THE CLASSIFIER, THUS 10 POSSIBLE CLASSES
model.add(Dense(10, activation='softmax'))

# https://keras.io/metrics/
model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy']) # we can add in additional metrics https://keras.io/metrics/

model.fit(x_train,y_cat_train,epochs=10,validation_data=(x_test,y_cat_test))

当我运行 model.fit 行时，我得到以下信息：

UnknownError                              Traceback (most recent call last)
<ipython-input-37-0eafbb732ade> in <module>
----> 1 model.fit(x_train,y_cat_train,epochs=10,validation_data=(x_test,y_cat_test))

~\anaconda3\envs\GPU\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\GPU\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\GPU\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\GPU\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\GPU\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\GPU\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
    597       # In this case we have created variables on the first call, so we run the
    598       # defunned version which is guaranteed to never create variables.
--> 599       return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
    600     elif self._stateful_fn is not None:
    601       # Release the lock early so that multiple threads can perform the call

~\anaconda3\envs\GPU\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\GPU\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\GPU\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\GPU\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\GPU\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\GPU\lib\site-packages\six.py in raise_from(value, from_value)

UnknownError:  Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
     [[node sequential/conv2d/Conv2D (defined at <ipython-input-36-6ec5ba2e7ade>:1) ]] [Op:__inference_distributed_function_788]

Function call stack:
distributed_function

我想澄清一下，我之前在常规 tensorflow 上运行过这个 CNN 没有问题，而这个新安装的 tensorflow-gpu 可以在 ANN 和 RNN 上运行。此外，这是我的规格和安装版本：

张量流 2.1
凯拉斯 2.3.1
CudNN 7.6.5
cudatoolkit 10.1.243
显卡：英伟达 2070

如果需要任何其他信息，请告诉我，谢谢！

标签： pythontensorflowkeras

python - 我的 tensorflow-gpu 安装不适用于 CNN

问题描述

解决方案

推荐阅读