在解决问题之前，我们先总结一下你正在处理的数据集。根据你的描述，我创建了一个DataFrame可能与你的类似的示例

import pandas as pd

dataset_size = 500
train_idx,val_idx = train_test_split(range(dataset_size),test_size=0.2,) 

# create an example DataFrame that I assume will be resemble yours 
example_df = pd.DataFrame({'vids':np.random.randint(0,10000,dataset_size)})
# create feature columns 
for ind in range(14): example_df['feature_%i' % ind] = np.random.rand(dataset_size)
# each cell contains a list 
example_df['text'] = np.random.randint(dataset_size)
example_df['text'] = example_df['text'].astype('object')
for ind in range(dataset_size):example_df.at[ind,'text'] = np.random.rand(768).tolist()
# create the label column
example_df['label'] = np.random.randint(low=0,high=5,size=dataset_size)

# extract information from the dataframe, and create data generators 
all_vids = example_df['vids'].values
feature_columns = ['feature_%i' % ind for ind in range(14)]
all_features = example_df[feature_columns].values
all_text = example_df['text'].values
all_labels = example_df['label'].values

如您所见，列text是一列列表，其中每个列表包含 768 个项目。列labels包含示例的标签，无论您使用独热编码还是其他类型的编码都没有关系，只要其形状与整个神经网络模型的输出层形状相匹配即可。列vids是一列seed用于动态生成随机图像的 s。

解决问题（基于上述数据集）

return {'feature':features,'text':text,'vid':vid},y您可以对方法使用此语法__getitem__，而不是堆叠三个输入数组。

为了解释这一点，我们首先构建一个类似于你的玩具模型

from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input,Dense,Flatten,Add


def features_part(x):
    y = Dense(14)(x)
    y = Dense(10,activation='linear')(y)
    return y

def text_part(x):
    y = Dense(768)(x)
    y = Dense(10,activation='linear')(y)
    return y

def vid_part(x):
    y = Flatten()(x)
    y = Dense(10,activation='linear')(y)
    return y

input_features = Input(shape=(14,),name='feature')
input_text = Input(shape=(768,),name='text')
input_vid = Input(shape=(3,244,244,),name='vid')

feature_block = features_part(input_features)
text_block = text_part(input_text)
vid_block = vid_part(input_vid)
added = Add()([feature_block,text_block,vid_block])
# you have five classes at the end of the day 
pred = Dense(1)(added)
# build model
model = Model(inputs=[input_features,input_text,input_vid],outputs=pred)
model.compile(loss='mae',optimizer='adam',metrics=['mae'])

这个模型最重要的是，我指定了三个输入层的名称

input_features = Input(shape=(14,),name='feature')
input_text = Input(shape=(768,),name='text')
input_vid = Input(shape=(3,244,244,),name='vid')

对于这个模型，你可以构建一个像

# provide a seed for generating a random image 
def fn2img(seed):
    np.random.seed(seed)
    # fake an image with three channels 
    return np.random.randint(low=0,high=255,size=(3,244,244))


class MultiInputDataGenerator(keras.utils.Sequence):

    def __init__(self, 
                 all_inds,labels, 
                 features,text,vid, 
                 shuffle=True):
        self.batch_size = 8
        self.labels = labels
        self.all_inds = all_inds
        self.shuffle = shuffle
        self.on_epoch_end()

        self.features = features
        self.text = text
        self.vid = vid

    def __len__(self): 
        return int(np.floor(len(self.all_inds) / self.batch_size))


    def __getitem__(self,index):
        indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]
        batch_indices = [self.all_inds[k] for k in indexes]
        features,text,vid,y = self.__data_generation(batch_indices)

        return {'feature':features,'text':text,'vid':vid},y

    def on_epoch_end(self):
        self.indexes = np.arange(len(self.all_inds))
        if self.shuffle == True:
            np.random.shuffle(self.indexes)

    def __data_generation(self,batch_indices):
        # Generate data
        features = self.features[batch_indices,:]
        # note that you need to stack the slice in order to reshape it to (num_samples,768)
        text = np.stack(self.text[batch_indices])
        # since batch_size is not a super large number, you can stack here
        vid = np.stack([fn2img(seed) for seed in self.vid[batch_indices]])
        y = self.labels[batch_indices]

        return features,text,vid,y

如您所见，该__getitem__方法返回一个字典{'feature':features,'text':text,'vid':vid},y。字典的键与三个输入层的名称相匹配。此外，随机图像是动态生成的。

为了确保一切正常，你可以运行以下脚本，

import numpy as np
import pandas as pd
from tensorflow import keras 
from sklearn.model_selection import train_test_split

from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input,Dense,Flatten,Add


# provide a seed for generating a random image
def fn2img(seed):
    np.random.seed(seed)
    # fake an image with three channels
    return np.random.randint(low=0,high=255,size=(3,244,244))


class MultiInputDataGenerator(keras.utils.Sequence):

    def __init__(self,
                 all_inds,labels,
                 features,text,vid,
                 shuffle=True):
        self.batch_size = 8
        self.labels = labels
        self.all_inds = all_inds
        self.shuffle = shuffle
        self.on_epoch_end()

        self.features = features
        self.text = text
        self.vid = vid

    def __len__(self):
        return int(np.floor(len(self.all_inds) / self.batch_size))


    def __getitem__(self,index):
        indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]
        batch_indices = [self.all_inds[k] for k in indexes]
        features,text,vid,y = self.__data_generation(batch_indices)

        return {'feature':features,'text':text,'vid':vid},y

    def on_epoch_end(self):
        self.indexes = np.arange(len(self.all_inds))
        if self.shuffle == True:
            np.random.shuffle(self.indexes)

    def __data_generation(self,batch_indices):
        # Generate data
        features = self.features[batch_indices,:]
        # note that you need to stack the slice in order to reshape it to (num_samples,768)
        text = np.stack(self.text[batch_indices])
        # since batch_size is not a super large number, you can stack here
        vid = np.stack([fn2img(seed) for seed in self.vid[batch_indices]])
        y = self.labels[batch_indices]

        return features,text,vid,y


# fake a dataset
dataset_size = 500
train_idx,val_idx = train_test_split(range(dataset_size),test_size=0.2,)

# create an example DataFrame that I assume will be resemble yours
example_df = pd.DataFrame({'vids':np.random.randint(0,10000,dataset_size)})
# create feature columns
for ind in range(14): example_df['feature_%i' % ind] = np.random.rand(dataset_size)
# each cell contains a list
example_df['text'] = np.random.randint(dataset_size)
example_df['text'] = example_df['text'].astype('object')
for ind in range(dataset_size):example_df.at[ind,'text'] = np.random.rand(768).tolist()
# create the label column
example_df['label'] = np.random.randint(low=0,high=5,size=dataset_size)

# extract information from the dataframe, and create data generators
all_vids = example_df['vids'].values
feature_columns = ['feature_%i' % ind for ind in range(14)]
all_features = example_df[feature_columns].values
all_text = example_df['text'].values
all_labels = example_df['label'].values

training_generator = MultiInputDataGenerator(train_idx,all_labels,all_features,all_text,all_vids)

# create model
def features_part(x):
    y = Dense(14)(x)
    y = Dense(10,activation='linear')(y)
    return y

def text_part(x):
    y = Dense(768)(x)
    y = Dense(10,activation='linear')(y)
    return y

def vid_part(x):
    y = Flatten()(x)
    y = Dense(10,activation='linear')(y)
    return y

input_features = Input(shape=(14,),name='feature')
input_text = Input(shape=(768,),name='text')
input_vid = Input(shape=(3,244,244,),name='vid')

feature_block = features_part(input_features)
text_block = text_part(input_text)
vid_block = vid_part(input_vid)
added = Add()([feature_block,text_block,vid_block])
# you have five classes at the end of the day 
pred = Dense(1)(added)
# build model
model = Model(inputs=[input_features,input_text,input_vid],outputs=pred)
model.compile(loss='mae',optimizer='adam',metrics=['mae'])

model.fit_generator(generator=training_generator,epochs=10)

print(model.history.history)