如何向CNN + LSTM网络添加其他数据

编程问答 2022-07-26

问题描述

我拥有以下网络（经过训练的CNN + LSTM可以对视频进行分类）：

 frames,channels,rows,columns = 5,3,224,224

  video = Input(shape=(frames,columns,channels))
  
  cnn_base = VGG16(input_shape=(rows,channels),weights="imagenet",include_top=True) #<=== include_top=True
  cnn_base.trainable = False

  cnn = Model(cnn_base.input,cnn_base.layers[-3].output,name="VGG_fm") # -3 is the 4096 layer
  encoded_frames = Timedistributed(cnn,name = "encoded_frames")(video)
  encoded_sequence = LSTM(256,name = "encoded_seqeunce")(encoded_frames)
  hidden_layer = Dense(1024,activation="relu",name = "hidden_layer")(encoded_sequence)
  outputs = Dense(10,activation="softmax")(hidden_layer)

  model = Model(video,outputs)

看起来像这样：

enter image description here

现在，我想将包含784个视频特征的一维矢量添加到最后一层。 我尝试将以下两行替换为：

  encoding_input = keras.Input(shape=(784,),name="Encoding",dtype='float') 
  sentence_features = layers.Dense(units = 60,name = 'sentence_features')(encoding_input)
  x = layers.concatenate([sentence_features,hidden_layer])
  outputs = Dense(10,activation="softmax")(x)

但是得到了错误：

ValueError: Graph disconnected: cannot obtain value for tensor Tensor("Sentence-Input-Encoding_3:0",shape=(None,784),dtype=float32) at layer "sentence_features". The following prevIoUs layers were accessed without issue: ['encoded_frames','encoded_seqeunce']

任何建议：

解决方法

您的网络现在有两个输入...别忘了将两个都传递给您的模型

return !data.length ? (<div>Loading..</div>) : (<div className="App">
  <Table columns={columns} data={data} />
</div>)

完整示例

model = Model([video,encoding_input],outputs)
deep-learningkeraskeraskeras-layerpython