Python ValueError:图形已断开连接：无法获取tensor tensor的值…已访问以下以前的层，但没有问题：[]

我一直在尝试使用Keras创建一个多输入模型，但出现了错误。这个想法是结合文本和相应的主题来预测情绪。代码如下：

import numpy as np
text = np.random.randint(5000, size=(442702, 200), dtype='int32')
topic = np.random.randint(2, size=(442702, 227), dtype='int32')
sentiment = to_categorical(np.random.randint(5, size=442702), dtype='int32')

from keras.models import Sequential
from keras.layers import Dense, Activation, Embedding, Flatten, GlobalMaxPool1D, Dropout, Conv1D
from keras.callbacks import ReduceLROnPlateau, EarlyStopping, ModelCheckpoint
from keras.losses import binary_crossentropy
from keras.optimizers import Adam


text_input = Input(shape=(200,), dtype='int32', name='text')
text_encoded = Embedding(input_dim=5000, output_dim=20, input_length=200)(text_input)
text_encoded = Dropout(0.1)(text_encoded)
text_encoded = Conv1D(300, 3, padding='valid', activation='relu', strides=1)(text_encoded)
text_encoded = GlobalMaxPool1D()(text_encoded)

topic_input = Input(shape=(227,), dtype='int32', name='topic')

concatenated = concatenate([text_encoded, topic_input])
sentiment = Dense(5, activation='softmax')(concatenated)

model = Model(inputs=[text_encoded, topic_input], outputs=sentiment)
# summarize layers
print(model.summary())
# plot graph
plot_model(model)

但是，这给了我以下错误：

TypeError:传递给'ConcatV2'Op的'values'的列表中的张量的类型[float32，int32]并不完全匹配。

现在，如果我将topic_输入的数据类型从“int32”更改为“float32”，则会出现不同的错误：

ValueError: Graph disconnected: cannot obtain value for tensor Tensor("text_37:0", shape=(?, 200), dtype=int32) at layer "text". The following previous layers were accessed without issue: []

另一方面，部分模型与顺序API配合得很好

model = Sequential()
model.add(Embedding(5000, 20, input_length=200))
model.add(Dropout(0.1))
model.add(Conv1D(300, 3, padding='valid', activation='relu', strides=1))
model.add(GlobalMaxPool1D())
model.add(Dense(227))
model.add(Activation('sigmoid'))

print(model.summary())

---

非常感谢您的指点

您的Keras功能API实现几乎没有问题

您应该将

连接

层用作

连接（轴=-1）（[text\u encoded，topic\u input]）

在连接层中，您试图组合

int32

张量和

float32

张量，这是不允许的。您应该做的是，

从keras.backend导入cast

和

连接=连接（axis=-1）（[text\u encoded，cast（topic\u input，'float32'））

您得到了变量冲突，有两个

情绪

变量，一个指向一个

to_category

输出，另一个指向最后一个

密集

层的输出

您的模型输入不能是中间张量，如

text\u-encoded

。它们应该来自

Input

层

为了帮助实现，这里有一个TF1.13中代码的工作版本（我不确定这是否正是您想要的）

from keras.utils import to_categorical
text = np.random.randint(5000, size=(442702, 200), dtype='int32')
topic = np.random.randint(2, size=(442702, 227), dtype='int32')
sentiment1 = to_categorical(np.random.randint(5, size=442702), dtype='int32')

from keras.models import Sequential
from keras.layers import Input, Dense, Activation, Embedding, Flatten, GlobalMaxPool1D, Dropout, Conv1D, Concatenate, Lambda
from keras.callbacks import ReduceLROnPlateau, EarlyStopping, ModelCheckpoint
from keras.losses import binary_crossentropy
from keras.optimizers import Adam
from keras.backend import cast
from keras.models import Model

text_input = Input(shape=(200,), dtype='int32', name='text')
text_encoded = Embedding(input_dim=5000, output_dim=20, input_length=200)(text_input)
text_encoded = Dropout(0.1)(text_encoded)
text_encoded = Conv1D(300, 3, padding='valid', activation='relu', strides=1)(text_encoded)
text_encoded = GlobalMaxPool1D()(text_encoded)

topic_input = Input(shape=(227,), dtype='int32', name='topic')

topic_float = Lambda(lambda x:cast(x, 'float32'), name='Floatconverter')(topic_input)

concatenated = Concatenate(axis=-1)([text_encoded, topic_float])
sentiment = Dense(5, activation='softmax')(concatenated)

model = Model(inputs=[text_input, topic_input], outputs=sentiment)
# summarize layers
print(model.summary())

---

希望这些帮助。

您确定不使用

输入=[text\u input，topic\u input]

而不是

输入=[text\u encoded，topic\u input]

？