如何管理通过以下错误执行的代码？答案

【问题标题】：how to manage the code which does through the following error?如何管理通过以下错误执行的代码？
【发布时间】：2020-07-20 23:07:34
【问题描述】：

我在我的个人系统中运行生成对抗网络，我收到如下错误，这可能是因为 GPU 访问问题，如此链接中所述：(Function call stack: keras_scratch_graph Error)

由于我想在我的个人系统中运行不包含 GPU 的代码，那么如何管理代码不应访问 GPU？

此链接中提供了 python 代码：(https://github.com/eriklindernoren/Keras-GAN/tree/master/pix2pix)，其中运行代码存在于 pix2pix.py 文件中。

产生的错误如下：

C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\keras\engine\training.py:297: UserWarning: Discrepancy between trainable weights and collected trainable weights, did you set `model.trainable` without calling `model.compile` after ?
  'Discrepancy between trainable weights and collected trainable'
2020-04-08 17:42:33.366720: W tensorflow/core/common_runtime/base_collective_executor.cc:217] BaseCollectiveExecutor::StartAbort Failed precondition: Error while reading resource variable _AnonymousVar131 from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/_AnonymousVar131/class tensorflow::Var does not exist.
     [[{{node mul_33/ReadVariableOp}}]]
Traceback (most recent call last):
  File "H:/data_rar_and_others/Code_For_GAN5/pix2pix.py", line 217, in <module>
    gan.train(epochs=220, batch_size=4, sample_interval=50)
  File "H:/data_rar_and_others/Code_For_GAN5/pix2pix.py", line 165, in train
    d_loss_real = self.discriminator.train_on_batch([imgs_A, imgs_B], valid)
  File "C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\keras\engine\training.py", line 1514, in train_on_batch
    outputs = self.train_function(ins)
  File "C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\tensorflow_core\python\keras\backend.py", line 3727, in __call__
    outputs = self._graph_fn(*converted_inputs)
  File "C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\tensorflow_core\python\eager\function.py", line 1551, in __call__
    return self._call_impl(args, kwargs)
  File "C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\tensorflow_core\python\eager\function.py", line 1591, in _call_impl
    return self._call_flat(args, self.captured_inputs, cancellation_manager)
  File "C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\tensorflow_core\python\eager\function.py", line 1692, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
  File "C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\tensorflow_core\python\eager\function.py", line 545, in call
    ctx=ctx)
  File "C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\tensorflow_core\python\eager\execute.py", line 67, in quick_execute
    six.raise_from(core._status_to_exception(e.code, message), None)
  File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.FailedPreconditionError:  Error while reading resource variable _AnonymousVar131 from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/_AnonymousVar131/class tensorflow::Var does not exist.
     [[node mul_33/ReadVariableOp (defined at C:\ProgramData\Anaconda2\envs\GaitRecognitionCNN-master13\lib\site-packages\keras\backend\tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_6898]

Function call stack:
keras_scratch_graph

【问题讨论】：

标签： python tensorflow keras

【解决方案1】：

当我更改了这个错误已经解决了

from keras.optimizers import Adam

以下

from tensorflow.keras.optimizers import Adam

【讨论】：