如何解决“输入数组应具有与目标数组相同数量的样本”

Question

使用keras imagedatagenerator加载数据，并构建具有keras图层的Unet模型，

如何解决值错误以及如何重塑输入图像？

下面是代码：

 #def gen(train_image,train_mask,val_images,val_mask):
data_gen_args = dict(#featurewise_center=True,
                     #featurewise_std_normalization=True,
                     rotation_range=90,
                     width_shift_range=0.1,
                     height_shift_range=0.1,
                     zoom_range=0.2)

image_datagen = ImageDataGenerator(**data_gen_args)
mask_datagen = ImageDataGenerator(**data_gen_args)
vimage_datagen = ImageDataGenerator(**data_gen_args)
vmask_datagen = ImageDataGenerator(**data_gen_args)
# Provide the same seed and keyword arguments to the fit and flow methods
seed = 1

#image_datagen.fit(images, augment=True, seed=seed)
image_generator = image_datagen.flow_from_directory(
    '/content/drive/My Drive/2019 github projects/dataset1/train_images',
    class_mode=None,target_size=(256,256),
    seed=seed)

mask_generator = mask_datagen.flow_from_directory(
    '/content/drive/My Drive/2019 github projects/dataset1/train_masl',
    class_mode=None,target_size=(256,256),
    seed=seed)

vimage_generator = image_datagen.flow_from_directory(
    '/content/drive/My Drive/2019 github projects/dataset1/test',
    class_mode=None,target_size=(256, 256),
    seed=seed)

vmask_generator = mask_datagen.flow_from_directory(
    '/content/drive/My Drive/2019 github projects/dataset1/mask_test',
    class_mode=None,target_size=(256, 256),seed=seed)

# combine generators into one which yields image and masks

train_generator = zip(image_generator, mask_generator)
val_generator = zip(vimage_generator,vmask_generator)


deaclred unet model

model_checkpoint = ModelCheckpoint('unet_membrane.hdf5', monitor='loss',verbose=1, save_best_only=True)
model.fit_generator(train_generator,steps_per_epoch=200,epochs=5,callbacks=[model_checkpoint])

以下是我面临的错误：

ValueError: Input arrays should have the same number of samples as target arrays. Found 15 input samples and 32 target samples.