Keras fit_generator 产生异常：生成器的输出应该是元组（x，y，sample_weight）或（x，y）。发现：[[[[ 0.86666673

我正在尝试为非 MNIST、非 Imagenet 数据构建一个自动编码器。使用https://blog.keras.io/building-autoencoders-in-keras.html https://blog.keras.io/building-autoencoders-in-keras.html作为我的基地。但是，我收到以下错误。

**Exception: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: [[[[ 0.86666673  0.86666673  0.86666673 ...,  0.62352943  0.627451
     0.63137257]
   [ 0.86666673  0.86666673  0.86666673 ...,  0.63137257  0.627451
     0.627451  ]
   [ 0.86666673  0.86666673  0.86666673 ...,  0.63137257  0.627451
     0.62352943]
   ...,**

由于这是一个自动编码器，因此在我的数据生成器中，使用了类模式=无。我的代码如下。

from keras.layers import Input, Dense, Convolution2D, MaxPooling2D,   UpSampling2D,Activation, Dropout, Flatten
from keras.models import Model,Sequential
from keras.preprocessing.image import ImageDataGenerator 
import numpy as np
import os
import h5py


img_width=140 
img_height=140
train_data_dir=r'SitePhotos\train'
valid_data_dir=r'SitePhotos\validation'
input_img = Input(batch_shape=(32,3, img_width, img_width))

x = Convolution2D(16, 3, 3, activation='relu', border_mode='same')(input_img)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x)
encoded = MaxPooling2D((2, 2), border_mode='same')(x)

# at this point the representation is (8, 4, 4) i.e. 128-dimensional

x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x)
x = UpSampling2D((2, 2))(x)
x = Convolution2D(16, 3, 3, activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Convolution2D(1, 3, 3, activation='sigmoid', border_mode='same')(x)

autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='mse')



valid_datagen = ImageDataGenerator(rescale=1./255)
train_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        train_data_dir,
        target_size=(img_width, img_height),
        batch_size=32,
        class_mode=None,
        shuffle=True)


valid_generator = valid_datagen.flow_from_directory(
        valid_data_dir,
        target_size=(img_width, img_height),
        batch_size=32,
        class_mode=None,
        shuffle=True)

autoencoder.fit_generator(train_generator,
                nb_epoch=50,                
                validation_data=valid_generator,
                samples_per_epoch=113,
                nb_val_samples=32
                )

真正的解决方案显然在于 @skottapa 提出的 Keras 问题。

https://github.com/fchollet/keras/issues/4260 https://github.com/fchollet/keras/issues/4260

rodgzilla 提供了更新的 ImageDataGenerator，添加了 class_mode='input' 来解决该问题。

好处是您可以将修改向后移植到旧的 Keras 版本。可以在这里下载稍微修改过的图像模块：

https://gist.github.com/gsdefender/293db0987a800cf1b103b7777966f8af https://gist.github.com/gsdefender/293db0987a800cf1b103b7777966f8af