Can't understand: ValueError: Graph disconnected: cannot obtain value for tensor Tensor

Question

我写了一个类似于这段代码的架构： 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, visual_features, et_features],
      outputs=[group_pred]
      # outputs=[group_pred, score_pred],
  )

但我收到错误消息：

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？

Answer 1

构建模型时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]

此处为完整模型

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, 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_encoding_input, visual_features_input, et_features_input],
  outputs=[group_pred]
  # outputs=[group_pred, score_pred],
)

hybrid_model.summary()

Can't understand: ValueError: Graph disconnected: cannot obtain value for tensor Tensor

Can't understand: ValueError: Graph disconnected: cannot obtain value for tensor Tensor

python

tensorflow

keras

keras-layer

tf.keras