ValueError：您传递给模型的Numpy数组列表不是模型预期的大小。多输入和输出

Question

我得到了如标题所示的错误，当我试图用2个输入训练一个U-Net并且预期输出也是2个时，Id为2个输入创建了两个训练生成器，如这段代码所示。< / p>

def trainGenerator1(batch_size,train_path1=('data\\membrane\\dataroad\\train'), mask_folder1= ('data\\membrane\\dataroad\\train\\ label'),image_folder1= ('data\\membrane\\dataroad\\train\\image'),mask_folder2= ('data\\membrane\\datacenterline\\train\\label'),image_color_mode1 = "rgb", 
                mask_color_mode1 = "grayscale", image_save_prefix  = "image", mask_save_prefix  = "mask",
                flag_multi_class = False,num_class = 2,save_to_dir = None,image_size1 = (224,224),seed = 1):
'''
can generate image and mask at the same time
use the same seed for image_datagen and mask_datagen to ensure the transformation for image and mask is the same
if you want to visualize the results of generator, set save_to_dir = "your path"
'''
data_gen_args1 = dict(rotation_range=0.2,
                width_shift_range=0.05,
                height_shift_range=0.05,
                shear_range=0.05,
                zoom_range=0.05,
                horizontal_flip=True,
                vertical_flip=True, 
                fill_mode='nearest') 



image_datagen1 = ImageDataGenerator(**data_gen_args1)
mask_datagen1 = ImageDataGenerator(**data_gen_args1)




image_generator1 = image_datagen1.flow_from_directory(

    train_path1,
    classes = [image_folder1],
    class_mode = None,
    color_mode = "rgb",
    target_size = image_size1,
    batch_size = 2,
    save_to_dir = save_to_dir,
    save_prefix  = image_save_prefix,
    seed = seed)


mask_generator1 = mask_datagen1.flow_from_directory(

    train_path1,
    classes = [mask_folder1],
    class_mode = None,
    color_mode = "grayscale",
    target_size = image_size1,
    batch_size = 2,
    save_to_dir = save_to_dir,
    save_prefix  = mask_save_prefix,
    seed = seed)


train_generator1 = zip(image_generator1, mask_generator1)
for (img1,mask1) in train_generator1:
    img1,mask1 = adjustData(img1,mask1,flag_multi_class,num_class)
    yield (img1,mask1)

其中的AdjustData如

所示

def adjustData(img,mask,flag_multi_class,num_class):
if(flag_multi_class):
    img = img / 255
    mask = mask[:,:,:,0] if(len(mask.shape) == 4) else mask[:,:,0]
    new_mask = np.zeros(mask.shape + (num_class,))
    for i in range(num_class):
        #for one pixel in the image, find the class in mask and convert it into one-hot vector
        #index = np.where(mask == i)
        #index_mask = (index[0],index[1],index[2],np.zeros(len(index[0]),dtype = np.int64) + i) if (len(mask.shape) == 4) else (index[0],index[1],np.zeros(len(index[0]),dtype = np.int64) + i)
        #new_mask[index_mask] = 1
        new_mask[mask == i,i] = 1
    new_mask = np.reshape(new_mask,(new_mask.shape[0],new_mask.shape[1]*new_mask.shape[2],new_mask.shape[3])) if flag_multi_class else np.reshape(new_mask,(new_mask.shape[0]*new_mask.shape[1],new_mask.shape[2]))
    mask = new_mask
elif(np.max(img) > 1):
    img = img / 255
    mask = mask /255
    mask[mask > 0.5] = 1
    mask[mask <= 0.5] = 0
return (img,mask)

并结合两个生成器

myGene1 = trainGenerator1(2,'data\\membrane\\dataroad\\train','image','label',   data_gen_args1,save_to_dir = None)

myGene2 = trainGenerator2(2,'data\\membrane\\datacenterline\\train','image','label', data_gen_args2,save_to_dir = None)

并如此处Joining two DirectoryIterators in Keras所示使用fit_generator，如图

class CombinedGen():
def __init__(self, *gens):
    self.gens = gens

def generate(self):
    while True:
        for myGene in self.gens:
            yield next(myGene)

def __len__(self):
    return sum([len(myGene) for myGene in self.gens])

cg = CombinedGen(myGene1, myGene2)
history= model.fit_generator(cg.generate(),steps_per_epoch=3240,epochs=150,callbacks=[model_checkpoint,tensorboard])

请提供任何帮助