Python 如何为图像集安装两个keras ImageDataGenerator

我正在为以下任务寻找解决方案或示例：

我有一组从不同角度拍摄的相同物体的图像。 我想用keras构建一个深度CNN，它可以获取两幅图像的集，分别对每幅图像执行数据增强，并将它们集成到一个连接的模型中

更详细的解释：

图像存储在HDF5文件中，具有以下形状：

data['Xp'] # shape=(3000, 224, 224, 3) #RGB images
data['Xs'] # shape=(3000, 224, 224, 3) #RGB images
data['Y']  # shape=(3000, 9) #categorical data.

现在，我想要一台发电机，它可以：

扰乱数据集的索引

然后拍摄照片和照片

数据中的类别增加了

X1\u列

，

X2\u列

将其单独馈送到具有以下结构的netwrok中：

代码

from keras.layers import Flatten, Dense, Input, Dropout, Convolution2D, MaxPooling2D, Merge


img_input = Input(shape=input_shape)
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input)
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)

# ... more network definition here ....

model1 = Model(img_input, x)
model2 = Model(img_input, x)

merged = Merge([model1, model2], mode='concat')

final_model = Sequential()
final_model.add(merged)
final_model.add(Dense(9, activation='softmax'))

我创建了以下生成器，该生成器生成用于向

安装该型号的发电机

def aug_train_iterator(Xp, Xs, Y, database_file=database_file, is_binary=True):
    from itertools import izip
    from keras.preprocessing.image import ImageDataGenerator

    seed = 7 #make sure that two iterators give same tomato each time...

    ig = ImageDataGenerator(dim_ordering='tf', rotation_range=90,
                                               width_shift_range=0.05,
                                               height_shift_range=0.05,
                                               zoom_range=0.05,
                                               fill_mode='constant',
                                               cval=0.0,
                                               horizontal_flip=True,
                                               rescale=1./255)


    for batch in izip(ig.flow(Xp,Y,  seed=seed), ig.flow(Xs, seed=seed)):
        for i in range(len(batch[0][0])):
            x1 = batch[0][0][i].reshape(1,224, 224, 3)
            x2 = batch[1][i].reshape(1, 224, 224, 3)
            y = batch[0][1][i].reshape(1,2)
            yield ([x1, x2], y)

gen = aug_train_iterator(Xp, Xs, Y)
final_model.fit_generator(gen, 1000, 20)

现在，当我试着适应模型时

def aug_train_iterator(Xp, Xs, Y, database_file=database_file, is_binary=True):
    from itertools import izip
    from keras.preprocessing.image import ImageDataGenerator

    seed = 7 #make sure that two iterators give same tomato each time...

    ig = ImageDataGenerator(dim_ordering='tf', rotation_range=90,
                                               width_shift_range=0.05,
                                               height_shift_range=0.05,
                                               zoom_range=0.05,
                                               fill_mode='constant',
                                               cval=0.0,
                                               horizontal_flip=True,
                                               rescale=1./255)


    for batch in izip(ig.flow(Xp,Y,  seed=seed), ig.flow(Xs, seed=seed)):
        for i in range(len(batch[0][0])):
            x1 = batch[0][0][i].reshape(1,224, 224, 3)
            x2 = batch[1][i].reshape(1, 224, 224, 3)
            y = batch[0][1][i].reshape(1,2)
            yield ([x1, x2], y)

gen = aug_train_iterator(Xp, Xs, Y)
final_model.fit_generator(gen, 1000, 20)

它实际上运行了一些图像。。。然后提出约15幅图像的错误：

Epoch 1/20
  15/1000 [..............................] - ETA: 606s - loss: 0.7001 - acc: 0.4000

Exception in thread Thread-44:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()
  File "/usr/lib/python2.7/threading.py", line 763, in run
    self.__target(*self.__args, **self.__kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 404, in data_generator_task
    generator_output = next(generator)
  File "<ipython-input-134-f128a127c7ce>", line 35, in aug_train_iterator
    for batch in izip(ig.flow(Xp,Y,  seed=seed), ig.flow(Xs, seed=seed)):
  File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 495, in next
    x = self.X[j]
  File "/usr/lib/python2.7/dist-packages/h5py/_hl/dataset.py", line 367, in __getitem__
    if self._local.astype is not None:
AttributeError: 'thread._local' object has no attribute 'astype'

纪元1/20
15/1000[……]-预计到达时间：606s-损失：0.7001-附件：0.4000
线程-44中的异常：
回溯（最近一次呼叫最后一次）：
文件“/usr/lib/python2.7/threading.py”，第810行，在引导程序内部
self.run（）
文件“/usr/lib/python2.7/threading.py”，第763行，运行中
自我目标（*自我参数，**自我参数）
文件“/usr/local/lib/python2.7/dist packages/keras/engine/training.py”，第404行，在数据生成器任务中
发电机输出=下一个（发电机）
文件“”，第35行，在aug_train_迭代器中
对于izip中的批次（ig.flow（Xp，Y，种子=种子），ig.flow（Xs，种子=种子））：
文件“/usr/local/lib/python2.7/dist packages/keras/preprocessing/image.py”，下一页第495行
x=自我。x[j]
文件“/usr/lib/python2.7/dist packages/h5py/_hl/dataset.py”，第367行，在__
如果self.\u local.astype不是None：
AttributeError:“thread.\u local”对象没有属性“astype”

---

问题是什么？

使用pickle\u safe=True解决了问题

好吧，我错过了keras文档中可能的解决方案。。。如果我将使用相同的seed和关键字参数来适应两个不同的生成器，它应该可以工作。我会测试它。似乎是h5py的问题，尝试通过

pip安装更新它——升级h5py

好吧，使用pickle\u safe=True似乎可以解决这个问题。不知道为什么