Skip to main content
 首页 » 编程设计

python之Keras fit_generator 产生异常 : output of generator should be a tuple(x, y, sample_weight) or (x, y)。发现 : [[[[ 0. 86666673

2025年04月02日7zfyouxi

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作为我的基地。但是,出现以下错误。

**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] 
   ...,** 

因为这是一个自动编码器,所以在我的数据生成器中,使用了 class mode=None。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 
                ) 

请您参考如下方法:

真正的解决方案显然是@skottapa 提出的这个 Keras 问题。

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

rodgzilla 提供了一个更新的 ImageDataGenerator,它添加了一个解决问题的 class_mode='input'。

好处是您可以将修改反向移植到旧的 Keras 版本。可以在此处下载稍微修改过的图像模块:

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