无法理解：ValueError：图形已断开：无法获得张量张量的值

问题描述

我写了一个类似于以下代码的架构： https://keras.io/guides/functional_api/#manipulate-complex-graph-topologie：

  visual_features_input = keras.Input(
    shape=(1000,),name="Visual-Input-FM",dtype='float') 
  et_features_input = keras.Input(
      shape=(12,name="ET-input",dtype='float') 
  sentence_encoding_input = keras.Input(
    shape=(784,name="Sentence-Input-Encoding",dtype='float') 
    
  et_features = layers.Dense(units = 12,name = 'et_features')(et_features_input)
  visual_features = layers.Dense(units = 100,name = 'visual_features')(visual_features_input)
  sentence_features = layers.Dense(units = 60,name = 'sentence_features')(sentence_encoding_input)

  x = layers.concatenate([sentence_features,visual_features,et_features],name = 'hybrid-concatenation')

  score_pred = layers.Dense(units = 1,name = "score")(x)
  group_pred = layers.Dense(units = 5,name="group")(x)
  
  # Instantiate an end-to-end model predicting both score and group
  hybrid_model = keras.Model(
      inputs=[sentence_features,outputs=[group_pred]
      # outputs=[group_pred,score_pred],)

但是我得到了错误：

ValueError: Graph disconnected: cannot obtain value for tensor Tensor("Sentence-Input-Encoding_2:0",shape=(None,784),dtype=float32) at layer "sentence_features". The following prevIoUs layers were accessed without issue: []

知道为什么吗？

解决方法

在构建模型时，请注意正确定义输入层

它们是inputs=[sentence_encoding_input,visual_features_input,et_features_input]而不是inputs=[sentence_features,visual_features,et_features]

这里是完整模型

from tensorflow import keras
from tensorflow.keras import layers

visual_features_input = keras.Input(
shape=(1000,),name="Visual-Input-FM",dtype='float') 
et_features_input = keras.Input(
  shape=(12,name="ET-input",dtype='float') 
sentence_encoding_input = keras.Input(
shape=(784,name="Sentence-Input-Encoding",dtype='float') 

et_features = layers.Dense(units = 12,name = 'et_features')(et_features_input)
visual_features = layers.Dense(units = 100,name = 'visual_features')(visual_features_input)
sentence_features = layers.Dense(units = 60,name = 'sentence_features')(sentence_encoding_input)

x = layers.concatenate([sentence_features,et_features],name = 'hybrid-concatenation')

score_pred = layers.Dense(units = 1,name = "score")(x)
group_pred = layers.Dense(units = 5,name="group")(x)

# Instantiate an end-to-end model predicting both score and group
hybrid_model = keras.Model(
  inputs=[sentence_encoding_input,et_features_input],outputs=[group_pred]
  # outputs=[group_pred,score_pred],)

hybrid_model.summary()