为什么我在 Keras 中创建堆叠合奏时出现图形断开值错误？
Why am I getting the Graph disconnected value error while creating a stacking ensemble in Keras?
我正在使用 Tensorflow 2.4 和 Keras 2.4.0。我正在使用 3 个针对三 class class 化任务训练的 Keras 模型创建堆叠集成。我正在使用串联合并，
其中将根据 3 个模型中的每一个模型预测的三个 class-概率创建一个 9 元素向量。我定义了一个隐藏层来将这个输入解释给一个元学习者，它构成了一个有 9 个神经元的隐藏层和一个输出层，这将使
自己的概率预测。每个模型的结构如下图所示：
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
reshape_1 (Reshape) (None, 49, 512) 0
_________________________________________________________________
lstm_1 (LSTM) (None, 49, 512) 2099200
_________________________________________________________________
batch_normalization_2 (Batch (None, 49, 512) 2048
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1605696
_________________________________________________________________
batch_normalization_3 (Batch (None, 64) 256
_________________________________________________________________
predictions (Dense) (None, 3) 195
=================================================================
代码如下：
def model1(model_input):
model1loss = load_model('model1.h5')
x = model1loss.output
model1 = Model(inputs=model1loss.input,
outputs=x,
name='model1')
return model1
model_loss1 = model1(model_input)
model_loss1.summary()
def model2(model_input):
model2loss = load_model('model2.h5')
x = model2loss.output
model2 = Model(inputs=model2loss.input,
outputs=x,
name='model2')
return model2
model_loss2 = model2(model_input)
model_loss2.summary()
def model3(model_input):
model3loss = load_model('model3.h5')
x = model3loss.output
model3 = Model(inputs=model3loss.input,
outputs=x,
name='model3')
return model3
model_loss3 = model3(model_input)
model_loss3.summary()
n_models = 3 #we have three models
def load_all_models(n_models):
all_models = list()
sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.95, nesterov=True)
model_loss1.load_weights('model1.h5')
model_loss1.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['accuracy'])
all_models.append(model_loss1)
model_loss2.load_weights('model2.h5')
model_loss2.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['accuracy'])
all_models.append(model_loss2)
model_loss3.load_weights('model3.h5')
model_loss3.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['accuracy'])
all_models.append(model_loss3)
return all_models
# load models
n_members = 3
members = load_all_models(n_members)
print('Loaded %d models' % len(members))
def define_stacked_model(members):
for i in range(len(members)):
model = members[i]
for layer in model.layers:
# make not trainable
layer.trainable = False
# rename to avoid 'unique layer name' issue
layer._name = 'ensemble_' + str(i+1) + '_' + layer.name
# define multi-headed input
ensemble_visible = [model.input]
# concatenate merge output from each model
ensemble_outputs = [model.output for model in members]
merge = concatenate(ensemble_outputs)
hidden = Dense(9, activation='relu')(merge) # three ouputs for 3 models, so 9 hidden neurons
output = Dense(3, activation='softmax')(hidden) #three classes
model = Model(inputs=ensemble_visible,
outputs=output,
name = 'stacking_ensemble')
# compile
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
return model
# define ensemble model
stacked_model = define_stacked_model(members)
stacked_model.summary()
在 运行 代码中，我得到如下所示的图形断开连接错误：
ValueError: Graph disconnected: cannot obtain value for tensor KerasTensor(type_spec=TensorSpec(shape=(None, 224, 224, 3), dtype=tf.float32, name='input_1'), name='input_1', description="created by layer 'ensemble_2_input_1'") at layer "ensemble_2_block1_conv1". The following previous layers were accessed without issue: ['ensemble_3_block1_conv1']
考虑到我们有一个接受相同输入并产生相同维度（在我们的例子中是二维）的输出的预训练模型列表：
input_dim = 10
members = [
Sequential([Dense(3, activation='softmax', input_shape=(input_dim,))]),
Sequential([Dense(3, activation='softmax', input_shape=(input_dim,))]),
Sequential([Dense(3, activation='softmax', input_shape=(input_dim,))])
] # we can suppose that they are pretrained
您可以通过这种简单的方式将它们合并在一起：
def define_stacked_model(members):
all_models = []
inp = Input((input_dim,)) # the same shared input for all the model
for i,model in enumerate(members):
for layer in model.layers:
# make not trainable
layer.trainable = False
# rename to avoid 'unique layer name' issue
layer._name = 'ensemble_' + str(i+1) + '_' + layer.name
all_models.append(model(inp))
merge = Concatenate()(all_models)
hidden = Dense(9, activation='relu')(merge)
output = Dense(3, activation='softmax')(hidden)
model = Model(inputs = inp,
outputs = output,
name = 'stacking_ensemble')
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
return model
定义虚拟数据并拟合：
n_samples = 100
X = np.random.uniform(0,1, (n_samples,input_dim))
y = tf.keras.utils.to_categorical(np.random.randint(0,3, (n_samples,)))
stacked_model = define_stacked_model(members)
stacked_model.fit(X,y, epochs=3)
我正在使用 Tensorflow 2.4 和 Keras 2.4.0。我正在使用 3 个针对三 class class 化任务训练的 Keras 模型创建堆叠集成。我正在使用串联合并， 其中将根据 3 个模型中的每一个模型预测的三个 class-概率创建一个 9 元素向量。我定义了一个隐藏层来将这个输入解释给一个元学习者，它构成了一个有 9 个神经元的隐藏层和一个输出层，这将使 自己的概率预测。每个模型的结构如下图所示：
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
reshape_1 (Reshape) (None, 49, 512) 0
_________________________________________________________________
lstm_1 (LSTM) (None, 49, 512) 2099200
_________________________________________________________________
batch_normalization_2 (Batch (None, 49, 512) 2048
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1605696
_________________________________________________________________
batch_normalization_3 (Batch (None, 64) 256
_________________________________________________________________
predictions (Dense) (None, 3) 195
=================================================================
代码如下：
def model1(model_input):
model1loss = load_model('model1.h5')
x = model1loss.output
model1 = Model(inputs=model1loss.input,
outputs=x,
name='model1')
return model1
model_loss1 = model1(model_input)
model_loss1.summary()
def model2(model_input):
model2loss = load_model('model2.h5')
x = model2loss.output
model2 = Model(inputs=model2loss.input,
outputs=x,
name='model2')
return model2
model_loss2 = model2(model_input)
model_loss2.summary()
def model3(model_input):
model3loss = load_model('model3.h5')
x = model3loss.output
model3 = Model(inputs=model3loss.input,
outputs=x,
name='model3')
return model3
model_loss3 = model3(model_input)
model_loss3.summary()
n_models = 3 #we have three models
def load_all_models(n_models):
all_models = list()
sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.95, nesterov=True)
model_loss1.load_weights('model1.h5')
model_loss1.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['accuracy'])
all_models.append(model_loss1)
model_loss2.load_weights('model2.h5')
model_loss2.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['accuracy'])
all_models.append(model_loss2)
model_loss3.load_weights('model3.h5')
model_loss3.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['accuracy'])
all_models.append(model_loss3)
return all_models
# load models
n_members = 3
members = load_all_models(n_members)
print('Loaded %d models' % len(members))
def define_stacked_model(members):
for i in range(len(members)):
model = members[i]
for layer in model.layers:
# make not trainable
layer.trainable = False
# rename to avoid 'unique layer name' issue
layer._name = 'ensemble_' + str(i+1) + '_' + layer.name
# define multi-headed input
ensemble_visible = [model.input]
# concatenate merge output from each model
ensemble_outputs = [model.output for model in members]
merge = concatenate(ensemble_outputs)
hidden = Dense(9, activation='relu')(merge) # three ouputs for 3 models, so 9 hidden neurons
output = Dense(3, activation='softmax')(hidden) #three classes
model = Model(inputs=ensemble_visible,
outputs=output,
name = 'stacking_ensemble')
# compile
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
return model
# define ensemble model
stacked_model = define_stacked_model(members)
stacked_model.summary()
在 运行 代码中，我得到如下所示的图形断开连接错误：
ValueError: Graph disconnected: cannot obtain value for tensor KerasTensor(type_spec=TensorSpec(shape=(None, 224, 224, 3), dtype=tf.float32, name='input_1'), name='input_1', description="created by layer 'ensemble_2_input_1'") at layer "ensemble_2_block1_conv1". The following previous layers were accessed without issue: ['ensemble_3_block1_conv1']
考虑到我们有一个接受相同输入并产生相同维度（在我们的例子中是二维）的输出的预训练模型列表：
input_dim = 10
members = [
Sequential([Dense(3, activation='softmax', input_shape=(input_dim,))]),
Sequential([Dense(3, activation='softmax', input_shape=(input_dim,))]),
Sequential([Dense(3, activation='softmax', input_shape=(input_dim,))])
] # we can suppose that they are pretrained
您可以通过这种简单的方式将它们合并在一起：
def define_stacked_model(members):
all_models = []
inp = Input((input_dim,)) # the same shared input for all the model
for i,model in enumerate(members):
for layer in model.layers:
# make not trainable
layer.trainable = False
# rename to avoid 'unique layer name' issue
layer._name = 'ensemble_' + str(i+1) + '_' + layer.name
all_models.append(model(inp))
merge = Concatenate()(all_models)
hidden = Dense(9, activation='relu')(merge)
output = Dense(3, activation='softmax')(hidden)
model = Model(inputs = inp,
outputs = output,
name = 'stacking_ensemble')
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
return model
定义虚拟数据并拟合：
n_samples = 100
X = np.random.uniform(0,1, (n_samples,input_dim))
y = tf.keras.utils.to_categorical(np.random.randint(0,3, (n_samples,)))
stacked_model = define_stacked_model(members)
stacked_model.fit(X,y, epochs=3)