Question

我想在GPU（gtx1050）上运行我的网络。但是由于某种原因，当我设置use_multiprocessing = True时，它将无法工作。是的，我已经安装了tensorflow-gpu。我正在共享代码和输出：

代码

# Importing the Keras libraries and packages
from keras.models import Sequential 
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense

# Initialising the CNN
classifier = Sequential()

# Step 1 - Convolution 

# border_mode is how feature detectors apply on the broders of the image
# order in tensor flowbackend starts with 2d array and then color channel
# activation functions used only to have positive values and NOT FOR NEURON ACTIVATION! 
classifier.add(Convolution2D(32, (3, 3), input_shape = (64, 64, 3), activation = 'relu'))

# Step 2 - Max Pooling
classifier.add(MaxPooling2D(pool_size = (2, 2)))

# Step 3 - Flattening
classifier.add(Flatten())

# Step 4 - Full Connection
classifier.add(Dense(activation = 'relu', units = 128 ))
# Output Layer
classifier.add(Dense(activation = 'sigmoid', units = 1))

# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

# Part 2 - Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(
        rescale=1./255, # all pixel values between 0-1
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1./255)

training_set = train_datagen.flow_from_directory('dataset/training_set',
                                                 target_size = (64, 64),
                                                 batch_size = 32,
                                                 class_mode = 'binary')


test_set = test_datagen.flow_from_directory('dataset/test_set',
                                            target_size = (64, 64),
                                            batch_size = 32,
                                            class_mode = 'binary')

classifier.fit_generator(training_set,
                         steps_per_epoch = 8000,
                         epochs = 25,
                         validation_data = test_set,
                         validation_steps = 2000,
                         use_multiprocessing=True)

输出我不明白这个输出。当我仅使用tensorflow在CPU上运行它时，它就可以工作，但速度确实很慢。在GPU上，这是实际输出

Using TensorFlow backend.
Found 8000 images belonging to 2 classes.
Found 2000 images belonging to 2 classes.
Epoch 1/25
Exception in thread Thread-29:
Traceback (most recent call last):
  File "C:\Users\manzo\Anaconda3\lib\threading.py", line 916, in _bootstrap_inner
    self.run()
  File "C:\Users\manzo\Anaconda3\lib\threading.py", line 864, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\manzo\Anaconda3\lib\site-packages\keras\utils\data_utils.py", line 548, in _run
    with closing(self.executor_fn(_SHARED_SEQUENCES)) as executor:
  File "C:\Users\manzo\Anaconda3\lib\site-packages\keras\utils\data_utils.py", line 522, in <lambda>
    initargs=(seqs,))
  File "C:\Users\manzo\Anaconda3\lib\multiprocessing\context.py", line 119, in Pool
    context=self.get_context())
  File "C:\Users\manzo\Anaconda3\lib\multiprocessing\pool.py", line 174, in __init__
    self._repopulate_pool()
  File "C:\Users\manzo\Anaconda3\lib\multiprocessing\pool.py", line 239, in _repopulate_pool
    w.start()
  File "C:\Users\manzo\Anaconda3\lib\multiprocessing\process.py", line 105, in start
    self._popen = self._Popen(self)
  File "C:\Users\manzo\Anaconda3\lib\multiprocessing\context.py", line 322, in _Popen
    return Popen(process_obj)
  File "C:\Users\manzo\Anaconda3\lib\multiprocessing\popen_spawn_win32.py", line 65, in __init__
    reduction.dump(process_obj, to_child)
  File "C:\Users\manzo\Anaconda3\lib\multiprocessing\reduction.py", line 60, in dump
    ForkingPickler(file, protocol).dump(obj)
TypeError: can't pickle _thread.lock objects

运行顺序神经网络时Tensorflow-gpu错误:(线程Thread-29中的异常:)

0 个答案: