错误“：预期输入是图像（numpy的阵列）以下的数据格式公约‘channels_first’”在Keras图像例

Question

我碰上以下错误，当我运行keras示例脚本：

C:\Users\johnd\AppData\Local\Programs\Python\Python35\lib\site-packages\keras\preprocessing\image.py:653: UserWarning: Expected input to be images (as Numpy array) following the data format convention "channels_first" (channels on axis 1), i.e. expected either 1, 3 or 4 channels on axis 1. However, it was passed an array with shape (60000, 1, 28, 28) (1 channels). 
    ' (' + str(x.shape[self.channel_axis]) + ' channels).') 

这是我的脚本：

from keras.datasets import mnist 
from keras.preprocessing.image import ImageDataGenerator 
from matplotlib import pyplot 
from keras import backend as K 
K.set_image_dim_ordering('th') 
# load data 
(X_train, y_train), (X_test, y_test) = mnist.load_data() 
# reshape to be [samples][pixels][width][height] 
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28) 
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28) 
# convert from int to float 
X_train = X_train.astype('float32') 
X_test = X_test.astype('float32') 
# define data preparation 
datagen = ImageDataGenerator(zca_whitening=True) 
# fit parameters from data 
datagen.fit(X_train) 
# configure batch size and retrieve one batch of images 
for X_batch, y_batch in datagen.flow(X_train, y_train, batch_size=9): 
    # create a grid of 3x3 images 
    for i in range(0, 9): 
     pyplot.subplot(330 + 1 + i) 
     pyplot.imshow(X_batch[i].reshape(28, 28), cmap=pyplot.get_cmap('gray')) 
    # show the plot 
    pyplot.show() 
    break 

你能告诉我什么是错的吗？

谢谢。

Answer 1

这不是一个错误，而是一个警告 - 我想你没有提到其余代码运行正常;这里是我运行脚本后获得：用(60000, 1, 28, 28)一个X_train.shape和类似的警告

：

/var/venv/tsats/local/lib/python2.7/site-packages/keras/preprocessing/image.py:648: 
UserWarning: Expected input to be images (as Numpy array) following the data format 
convention "channels_first" (channels on axis 1), i.e. expected either 1, 3 or 4 channels on 
axis 1. However, it was passed an array with shape (60000, 1, 28, 28) (1 channels). ' (' + str(x.shape[self.channel_axis]) + ' channels).') 

关闭该警告的检查结果显示，这是荒谬的：它要求的是通道在轴1上（它们是），并且它们在{1, 3, 4}中有一个值（它们的有效值为1）。显然这是一个Keras的bug - 我打开了一个issue - 但它不会影响其他代码和结果。

UPDATE：根据Keras Github中的response问题，这现在已经在master中修复了（尽管还没有测试过自己）。