图表已断开连接：无法获取张量张量输入Keras Python的值

Question

我有以下代码：# Declare the layersinp1 = Input(shape=input_shape, name="input1")inp2 = Input(shape=input_shape, name="input2")# 128 -> 64conv1_inp1 = Conv2D(start_neurons * 1, 3, activation="relu", padding="same")(inp1)conv1_inp2 = Conv2D(start_neurons * 1, 3, activation="relu", padding="same")(inp2)conv1 = Concatenate()([conv1_inp1, conv1_inp2])conv1 = Conv2D(start_neurons * 1, 3, activation="relu", padding="same")(conv1)conv1 = MaxPooling2D((2, 2))(conv1)conv1 = Dropout(0.25)(conv1)# 64 -> 32conv2 = Conv2D(start_neurons * 2, (3, 3), activation="relu", padding="same")(conv1)conv2 = Conv2D(start_neurons * 2, (3, 3), activation="relu", padding="same")(conv2)pool2 = MaxPooling2D((2, 2))(conv2)pool2 = Dropout(0.5)(pool2)# 32 -> 16conv3 = Conv2D(start_neurons * 4, (3, 3), activation="relu", padding="same")(pool2)conv3 = Conv2D(start_neurons * 4, (3, 3), activation="relu", padding="same")(conv3)pool3 = MaxPooling2D((2, 2))(conv3)pool3 = Dropout(0.5)(pool3)# 16 -> 8conv4 = Conv2D(start_neurons * 8, (3, 3), activation="relu", padding="same")(pool3)conv4 = Conv2D(start_neurons * 8, (3, 3), activation="relu", padding="same")(conv4)pool4 = MaxPooling2D((2, 2))(conv4)pool4 = Dropout(0.5)(pool4)# Middleconvm = Conv2D(start_neurons * 16, (3, 3), activation="relu", padding="same")(pool4)convm = Conv2D(start_neurons * 16, (3, 3), activation="relu", padding="same")(convm)# 8 -> 16deconv4 = Conv2DTranspose(start_neurons * 8, (3, 3), strides=(2, 2), padding="same")(convm)uconv4 = Concatenate()([deconv4, conv4])uconv4 = Dropout(0.5)(uconv4)uconv4 = Conv2D(start_neurons * 8, (3, 3), activation="relu", padding="same")(uconv4)uconv4 = Conv2D(start_neurons * 8, (3, 3), activation="relu", padding="same")(uconv4)并产生此错误：Graph disconnected: cannot obtain value for tensor Tensor("input_28:0", shape=(?, 128, 128, 1), dtype=float32) at layer "input_28". The following previous layers were accessed without issue: []输入具有相同的形状，在某些论坛中，他们说问题出在以下事实：输入来自2个不同的来源，因此破坏了您之前的链接。我真的不知道该如何解决。谁能帮我？

Answer 1

这是图形断开连接的地方（uconv2调用时未定义）：

# 32 -> 64

deconv2 = Conv2DTranspose(start_neurons * 2, (3, 3), strides=(2, 2), padding="same")(uconv3)

uconv2 = Conv2D(start_neurons * 2, (3, 3), activation="relu", padding="same")(uconv2)

Answer 2

解决此图错误的原因是我对此进行了更改：

x_in = Input(shape=(10,), name="InputLayer")

_ = order2_embs_model(x_in)

...

model = Model(inputs=x_in, outputs=Y, name='DeepFFM') 

对此：

model = Model(inputs=order2_embs_model.inputs, outputs=Y, name='DeepFFM')