Question

我修改了在这里找到的代码： https://github.com/geifmany/cifar-vgg/blob/master/cifar100vgg.py 使其可以与tf.keras一起使用，但是当我使用fit_generator时，出现设备或资源繁忙错误。我尝试使用tf.keras.models.Sequential.fit，但没有收到此错误。

from __future__ import print_function
import numpy as np
import os

from keras.datasets import cifar100
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten
from tensorflow.keras.layers import Conv2D, MaxPool2D, BatchNormalization
from tensorflow.keras import optimizers
from tensorflow.keras import regularizers

import tensorflow as tf
import tensorflow.keras as keras

def build_model(): 

def normalize(x,y):

def main():
    batch_size = 128
    maxepochs = 250
    learning_rate = 0.1
    lr_decay = 1e-6
    lr_drop = 20

    tf.logging.set_verbosity(tf.logging.INFO)
    os.environ["CUDA_VISIBLE_DEVICES"] = '0'

    (x_train, y_train), (x_test, y_test) = cifar100.load_data()
    x_train = x_train.astype('float32')
    x_test = x_test.astype('float32')
    x_train, x_test = normalize(x_train, x_test)

    y_train = keras.utils.to_categorical(y_train, num_classes)
    y_test = keras.utils.to_categorical(y_test, num_classes)

    model = build_model()

    def lr_scheduler(epoch):
        return learning_rate * (0.5 ** (epoch // lr_drop))

    reduce_lr = keras.callbacks.LearningRateScheduler(lr_scheduler)

    datagen = ImageDataGenerator(
        featurewise_center=False,  # set input mean to 0 over the dataset
        samplewise_center=False,  # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=15,  # randomly rotate images in the range (degrees, 0 to 180)
        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  # randomly flip images
        vertical_flip=False)  # randomly flip images

    datagen.fit(x_train)


    sgd = optimizers.SGD(lr=learning_rate, decay=lr_decay, momentum=0.9, nesterov=True)
    model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

    model.fit_generator(datagen.flow(x_train, y_train,
                                 batch_size=batch_size),
                    steps_per_epoch=None,
                    epochs=maxepochs,
                    use_multiprocessing=False,
                    validation_data=(x_test, y_test), callbacks=[reduce_lr], verbose=1)

这是我在训练结束后（250个时期之后）得到的错误：

Traceback (most recent call last):

 File "/BS/work/anaconda3/envs/gpu/lib/python3.6/multiprocessing/util.py", line 262, in _run_finalizers
    finalizer()

File "/BS/work/anaconda3/envs/gpu/lib/python3.6/multiprocessing/util.py", line 186, in __call__
    res = self._callback(*self._args, **self._kwargs)

File "/BS/work/anaconda3/envs/gpu/lib/python3.6/shutil.py", line 486, in rmtree
    _rmtree_safe_fd(fd, path, onerror)

File "/BS/work/anaconda3/envs/gpu/lib/python3.6/shutil.py", line 444, in _rmtree_safe_fd
    onerror(os.unlink, fullname, sys.exc_info())

File "/BS/work/anaconda3/envs/gpu/lib/python3.6/shutil.py", line 442, in _rmtree_safe_fd
    os.unlink(name, dir_fd=topfd)

OSError: [Errno 16] Device or resource busy: '.nfs00000000000890d30000a675'

Answer 1

它正在尝试删除一些用于在进程之间进行通信的临时目录，但是该目录已通过NFS挂载，并且其中的一些文件已打开。 NFS不支持在打开文件时取消链接的Unix惯用语，因此NFS客户端通过重命名文件来模拟它，并在文件关闭后真正将其删除。

当然，递归删除也可以通过尝试删除重命名的文件来解决这个问题。在某些情况下，它只是再次重命名（如果递归删除最终尝试使用ENOTEMPTY，则会产生rmdir），但您却得到了EBUSY（也许表明文件正在执行？）。 / p>

在某些情况下，这可能是由交互活动引起的，但是如果不是这个问题，请确保清除所有资源并加入进程，然后再运行这种自动清除。

出现OSError：[Errno 16]设备或资源繁忙：'在使用tf.keras.models.Sequential.fit_generator时

1 个答案: