图表断开：无法获取张量的值 Tensor("conv2d_1_input:0", shape=(?, 128, 128, 1), dtype=float32)

Question

我正在尝试实现一个自动编码器，它可以获取 3 个不同的输入并融合这三个图像。我想在编码器中获取层的输出并将其与解码器中的层连接，但是当我运行它时，我得到图形断开错误。 这是我的代码：

def create_model(input_shape):
   input_1 = keras.layers.Input(input_shape)
   input_2 = keras.layers.Input(input_shape)
   input_3 = keras.layers.Input(input_shape)

   network = keras.models.Sequential([
   keras.layers.Conv2D(32, (7, 7), activation=tf.nn.relu, padding='SAME',input_shape=input_shape),
   keras.layers.Conv2D(32, (7, 7), activation=tf.nn.relu, padding='SAME', name = 'a'),
   keras.layers.AvgPool2D((2, 2)),
   keras.layers.BatchNormalization(),
   keras.layers.Dropout(0.3)])

   encoded_1 = network(input_1)
   encoded_2 = network(input_2)
   encoded_3 = network(input_3)

   a = network.get_layer('a').output

   x = keras.layers.Concatenate()([encoded_1,encoded_2,encoded_3])

   x = keras.layers.Conv2D(32, (3, 3), activation=tf.nn.relu, padding='SAME')(x)
   x = keras.layers.UpSampling2D((2,2))(x)
   x = keras.layers.BatchNormalization()(x)
   x = keras.layers.Dropout(0.3)(x)

   x = keras.layers.Concatenate()([x,a])
   x = keras.layers.Conv2D(32, (3, 3), activation=tf.nn.relu, padding='SAME')(x)
   x = keras.layers.UpSampling2D((2,2))(x)
   x = keras.layers.BatchNormalization()(x)
   x = keras.layers.Dropout(0.3)(x)

   decoded = keras.layers.Conv2D(3, (3, 3), activation=tf.nn.relu, padding='SAME')(x)

   final_net= keras.models.Model(inputs=[input_1,input_2,input_3],outputs=decoded)
   return final_net

错误是：

图形断开连接：无法在“conv2d_1_input”层获取张量 Tensor("conv2d_1_input:0", shape=(?, 128, 128, 1), dtype=float32) 的值。访问以下之前的层没有问题：['input_6', 'input_5', 'input_4', 'sequential_1', 'sequential_1', 'sequential_1', 'concatenate', 'conv2d_2']

这是因为连接了 [x,a]。我试图从三个图像中获取层的输出，例如：

encoder_1.get_layer('a').output
encoder_2.get_layer('a').output
encoder_3.get_layer('a').output

但我得到一个错误“'Tensor' object has no attribute 'output'”

Answer 1

如果需要获取a1、a2 和a3 输出，则需要创建子网。并且可以连接x和a如下。

def create_model(input_shape):
   input_1 = keras.layers.Input(input_shape)
   input_2 = keras.layers.Input(input_shape)
   input_3 = keras.layers.Input(input_shape)

   network = keras.models.Sequential([
   keras.layers.Conv2D(32, (7, 7), activation=tf.nn.relu, padding='SAME',input_shape=input_shape),
   keras.layers.Conv2D(32, (7, 7), activation=tf.nn.relu, padding='SAME', name = 'a'),
   keras.layers.AvgPool2D((2, 2)),
   keras.layers.BatchNormalization(),
   keras.layers.Dropout(0.3)])

   encoded_1 = network(input_1)
   encoded_2 = network(input_2)
   encoded_3 = network(input_3)

   subnet = keras.models.Sequential()
   for l in network.layers:
     subnet.add(l)
     if l.name == 'a': break

   a1 = subnet(input_1)
   a2 = subnet(input_2)
   a3 = subnet(input_3)

   x = keras.layers.Concatenate()([encoded_1,encoded_2,encoded_3])
   a = keras.layers.Concatenate()([a1,a2,a3])

   x = keras.layers.Conv2D(32, (3, 3), activation=tf.nn.relu, padding='SAME')(x)
   x = keras.layers.UpSampling2D((2,2))(x)
   x = keras.layers.BatchNormalization()(x)
   x = keras.layers.Dropout(0.3)(x)

   x = keras.layers.Concatenate()([x,a])
   x = keras.layers.Conv2D(32, (3, 3), activation=tf.nn.relu, padding='SAME')(x)
   x = keras.layers.UpSampling2D((2,2))(x)
   x = keras.layers.BatchNormalization()(x)
   x = keras.layers.Dropout(0.3)(x)

   decoded = keras.layers.Conv2D(3, (3, 3), activation=tf.nn.relu, padding='SAME')(x)

   final_net= keras.models.Model(inputs=[input_1,input_2,input_3],outputs=decoded)
   return final_net