Question

用于tensorflow-2的相对较新的keras-tuner模块导致错误“无法创建NewWriteableFile”。 tuner.search函数正在运行，只有在试用完成后才引发错误。这是来自senddex Youtube频道的教程。

代码如下：

from tensorflow import keras
from tensorflow.keras.datasets import fashion_mnist
from tensorflow.keras.layers import Dense, Conv2D, MaxPooling2D, Activation, Flatten
from kerastuner.tuners import RandomSearch
from kerastuner.engine.hyperparameters import HyperParameters
import matplotlib.pyplot as plt
import time

(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()

x_train = x_train[:1000].reshape(-1, 28, 28, 1)
x_test = x_test[:100].reshape(-1, 28, 28, 1)
y_train = y_train[:1000]
y_test = y_test[:100]
# x_train = x_train.reshape(-1, 28, 28, 1)
# x_test = x_test.reshape(-1, 28, 28, 1)

LOG_DIR = f"{int(time.time())}"


def build_model(hp):  
    model = keras.models.Sequential()
    model.add(Conv2D(hp.Int("layer1_channels", min_value=32,
            max_value=256, step=32), (3,3), input_shape=x_train.shape[1:]))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    for i in range(hp.Int("n_layers", 1, 4)):
        model.add(Conv2D(hp.Int(f"conv_{i}_channels", min_value=32,
            max_value=256, step=32), (3,3)))
    model.add(Flatten())
    model.add(Dense(10))
    model.add(Activation('softmax'))
    model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
    return model

tuner = RandomSearch(build_model, 
                    objective = "val_accuracy", 
                    max_trials = 1, 
                    executions_per_trial = 1, 
                    directory = LOG_DIR,
                    project_name = 'junk')

tuner.search(x_train,
            y_train,
            epochs=1,
            batch_size=64,
            validation_data=(x_test, y_test))

这是回溯打印输出：

(tf_2.0) C:\Users\redex\OneDrive\Documents\Education\Sentdex Tutorials\Keras-Tuner>C:/Users/redex/Anaconda3/envs/tf_2.0/python.exe "c:/Users/redex/OneDrive/Documents/Education/Sentdex Tutorials/Keras-Tuner/keras-tuner.py"

2019-12-21 10:07:47.556531: I tensorflow/core/platform/cpu_feature_guard.cc:145] This TensorFlow binary is optimized with Intel(R) MKL-DNN to use the following CPU instructions in performance critical operations:  AVX AVX2
To enable them in non-MKL-DNN operations, rebuild TensorFlow with the appropriate compiler flags. 
2019-12-21 10:07:47.574699: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 8. Tune using inter_op_parallelism_threads for best performance.

Train on 1000 samples, validate on 100 samples
 960/1000 [===========================>..] - ETA: 0s - loss: 64.0616 - accuracy: 0.2844

2019-12-21 10:07:55.080024: W tensorflow/core/framework/op_kernel.cc:1622] OP_REQUIRES failed at save_restore_v2_ops.cc:109 : Not found: Failed to create a NewWriteableFile: 1576951667\junk\trial_c5a5436b1d28a85446ce55c8d13f9657\checkpoints\epoch_0\checkpoint_temp_8a230a5ae2d046098456d1fdfc696690/part-00000-of-00001.data-00000-of-00001.tempstate15377864750281844169 : The system cannot find the path specified.
; No such process
Traceback (most recent call last):
  File "c:/Users/redex/OneDrive/Documents/Education/Sentdex Tutorials/Keras-Tuner/keras-tuner.py", line 65, in <module>
    validation_data=(x_test, y_test))
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\kerastuner\engine\base_tuner.py", line 122, in search
    self.run_trial(trial, *fit_args, **fit_kwargs)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\kerastuner\engine\multi_execution_tuner.py", line 95, in run_trial
    history = model.fit(*fit_args, **fit_kwargs, callbacks=callbacks)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 728, in fit
    use_multiprocessing=use_multiprocessing)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 372, in fit
    prefix='val_')
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\contextlib.py", line 119, in __exit__
    next(self.gen)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 685, in on_epoch
    self.callbacks.on_epoch_end(epoch, epoch_logs)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\keras\callbacks.py", line 298, in on_epoch_end
    callback.on_epoch_end(epoch, logs)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\keras\callbacks.py", line 965, in on_epoch_end
    self._save_model(epoch=epoch, logs=logs)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\keras\callbacks.py", line 999, in _save_model
    self.model.save_weights(filepath, overwrite=True)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\keras\engine\network.py", line 1090, in save_weights
    self._trackable_saver.save(filepath, session=session)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\training\tracking\util.py", line 1155, in save
    file_prefix=file_prefix_tensor, object_graph_tensor=object_graph_tensor)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\training\tracking\util.py", line 1103, in _save_cached_when_graph_building
    save_op = saver.save(file_prefix)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\training\saving\functional_saver.py", line 230, in save
    sharded_saves.append(saver.save(shard_prefix))
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\training\saving\functional_saver.py", line 72, in save
    return io_ops.save_v2(file_prefix, tensor_names, tensor_slices, tensors)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\ops\gen_io_ops.py", line 1932, in save_v2
    ctx=_ctx)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\lib\site-packages\tensorflow_core\python\ops\gen_io_ops.py", line 1969, in save_v2_eager_fallback
    ctx=_ctx, name=name)
  File "C:\Users\redex\Anaconda3\envs\tf_2.0\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.NotFoundError: Failed to create a NewWriteableFile: 1576951667\junk\trial_c5a5436b1d28a85446ce55c8d13f9657\checkpoints\epoch_0\checkpoint_temp_8a230a5ae2d046098456d1fdfc696690/part-00000-of-00001.data-00000-of-00001.tempstate15377864750281844169 : The system cannot find the path specified.
; No such process [Op:SaveV2]

我的机器是Windows 10 keras-tuner文档指定了Tensorflow 2.0和Python 3.6，但我使用的是3.7.4。我想最近可以。我不是软件专家，所以这就是我所知道的一切，我们将提供任何帮助。

Answer 1

在Windows中使用kerastuner时出现了类似问题，并且已经解决：

第一个问题是日志目录的路径可能太长。我不得不减少它。
第二个问题是python（或tf）在带有斜杠的Windows中不起作用。但是kerastuner用反斜杠构成了路径。因此，我应该为路径提供反斜杠。我已经使用os.path.normpath（）方法做到了这一点：

tuner=RandomSearch(build_model,objective='val_accuracy',max_trials=10,directory=os.path.normpath('C:/'))
tuner.search(x_train,y_train,batch_size=256,epochs=30,validation_split=0.2,verbose=1)

现在我没有收到此错误。

Answer 2

在我的情况下，该路径超出了Windows中路径的最大长度，因为Keras Turner生成的路径的长度约为170。在我缩短文件夹后，它可以正常工作。

Answer 3

它将出现的问题是Windows问题。在这方面，在Linux环境中运行相同的代码没有问题。

Keras-tuner搜索功能引发无法创建NewWriteableFile错误

3 个答案: