合并 3 个深度网络并端到端训练

Question

我正在使用深度学习概念，但它是初学者，我正在尝试使用 3 个深度神经网络模型构建特征融合概念，我的想法是我试图从所有三个模型中获取特征并做在最后一个sigmoid层上分类然后得到结果，这是我运行的代码。

代码：

from keras.layers import Input, Dense
from keras.models import Model
from sklearn.model_selection import train_test_split
import numpy
# random seed for reproducibility
numpy.random.seed(2)
# loading load pima indians diabetes dataset, past 5 years of medical history
dataset = numpy.loadtxt('https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv', delimiter=",")
# split into input (X) and output (Y) variables, splitting csv data
X = dataset[:, 0:8]
Y = dataset[:, 8]
x_train, x_validation, y_train, y_validation = train_test_split(X, Y, test_size=0.20, random_state=5)
#create the input layer
input_layer = Input(shape=(8,))
A2 = Dense(8, activation='relu')(input_layer)
A3 = Dense(30, activation='relu')(A2)
B2 = Dense(40, activation='relu')(A2)
B3 = Dense(30, activation='relu')(B2)
C2 = Dense(50, activation='relu')(B2)
C3 = Dense(5, activation='relu')(C2)
merged = Model(inputs=[input_layer],outputs=[A3,B3,C3])
final_model = Dense(1, 
activation='sigmoid')(merged
final_model.compile(loss="binary_crossentropy",
              optimizer="adam", metrics=['accuracy'])
# call the function to fit to the data (training the network)
final_model.fit(x_train, y_train, epochs=2000, batch_size=50,
          validation_data=(x_validation, y_validation))
# evaluate the model
scores = final_model.evaluate(x_validation,y_validation)
print("\n%s: %.2f%%" % (final_model.metrics_names[1], scores[1] * 100))

这是我面临的错误

if x.shape.ndims is None:

AttributeError: 'Functional' object has no attribute 'shape'

请帮我解决这个问题，或者如果有人知道我应该使用什么代码，请告诉我我也愿意更改代码但不是概念谢谢。

---

更新

根据@M.Innat 的回答，我们尝试如下。我们的想法是我们首先构建 3 个模型，然后通过将这些模型与单个分类器连接来构建最终/组合模型。但我面临一个差异。当我训练每个模型时，它们给出了 90% 的结果，但是当我将它们组合起来时，它们几乎没有达到 60 或 70。

代码模型 1：

   model = Sequential()
    # input layer requires input_dim param
    model.add(Dense(10, input_dim=8, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(5, activation='relu'))
    # sigmoid instead of relu for final probability between 0 and 1
    model.add(Dense(1, activation='sigmoid'))
    
    # compile the model, adam gradient descent (optimized)
    model.compile(loss="binary_crossentropy",
                  optimizer="adam", metrics=['accuracy'])
    
    # call the function to fit to the data (training the network)
    model.fit(x_train, y_train, epochs=1000, batch_size=50,
              validation_data=(x_validation, y_validation))
    
    # evaluate the model
    
    scores = model.evaluate(X, Y)
    print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1] * 100))
    model.save('diabetes_risk_nn.h5')

模型 1 精度= 94.14%。与另外 2 个模型相同。

模型 2 精度= 93.62% 模型 3 精度= 92.71%

接下来，正如@M.Innat 建议的那样合并模型。在这里，我们使用上述模型 1、2、3 完成了该操作。但分数并不接近~90%。最终组合模型：

# Define Model A 
input_layer = Input(shape=(8,))
A2 = Dense(10, activation='relu')(input_layer)
A3 = Dense(50, activation='relu')(A2)
A4 = Dense(50, activation='relu')(A3)
A5 = Dense(50, activation='relu')(A4)
A6 = Dense(50, activation='relu')(A5)
A7 = Dense(50, activation='relu')(A6)
A8 = Dense(5, activation='relu')(A7)
model_a = Model(inputs=input_layer, outputs=A8, name="ModelA")

# Define Model B 
input_layer = Input(shape=(8,))
B2 = Dense(10, activation='relu')(input_layer)
B3 = Dense(50, activation='relu')(B2)
B4 = Dense(40, activation='relu')(B3)
B5 = Dense(60, activation='relu')(B4)
B6 = Dense(30, activation='relu')(B5)
B7 = Dense(50, activation='relu')(B6)
B8 = Dense(50, activation='relu')(B7)
B9 = Dense(5, activation='relu')(B8)
model_b = Model(inputs=input_layer, outputs=B9, name="ModelB")

# Define Model C
input_layer = Input(shape=(8,))
C2 = Dense(10, activation='relu')(input_layer)
C3 = Dense(50, activation='relu')(C2)
C4 = Dense(40, activation='relu')(C3)
C5 = Dense(40, activation='relu')(C4)
C6 = Dense(70, activation='relu')(C5)
C7 = Dense(50, activation='relu')(C6)
C8 = Dense(50, activation='relu')(C7)
C9 = Dense(60, activation='relu')(C8)
C10 = Dense(50, activation='relu')(C9)
C11 = Dense(5, activation='relu')(C10)
model_c = Model(inputs=input_layer, outputs=C11, name="ModelC")
all_three_models = [model_a, model_b, model_c]
all_three_models_input = Input(shape=all_three_models[0].input_shape[1:])

然后将这三个结合起来。

models_output = [model(all_three_models_input) for model in all_three_models]
Concat           = tf.keras.layers.concatenate(models_output, name="Concatenate")
final_out     = Dense(1, activation='sigmoid')(Concat)
final_model   = Model(inputs=all_three_models_input, outputs=final_out, name='Ensemble')
#tf.keras.utils.plot_model(final_model, expand_nested=True)
final_model.compile(loss="binary_crossentropy",
              optimizer="adam", metrics=['accuracy'])
# call the function to fit to the data (training the network)
final_model.fit(x_train, y_train, epochs=1000, batch_size=50,
          validation_data=(x_validation, y_validation))

# evaluate the model

scores = final_model.evaluate(x_validation,y_validation)
print("\n%s: %.2f%%" % (final_model.metrics_names[1], scores[1] * 100))
final_model.save('diabetes_risk_nn.h5')

但与他们给出 90% 的每个模型不同，这个组合最终模型的准确率约为 =70%

Answer 1

我想输出层是Dense(1, activation='sigmoid')。所以尝试这样的事情

# ...
merged = tf.keras.layers.concatenate([A3,B3,C3])
out = Dense(1, activation='sigmoid')(merged)
model = (input_layer, out)

model.fit(x_train, y_train, ...)

Answer 2

根据您的代码，只有一个模型（不是三个）。通过查看您尝试过的输出，我认为您正在寻找这样的东西：

数据集

import tensorflow as tf 
from tensorflow.keras.layers import Input, Dense
from tensorflow.keras.models import Model
from sklearn.model_selection import train_test_split
import numpy

# random seed for reproducibility
numpy.random.seed(2)
# loading load pima indians diabetes dataset, past 5 years of medical history
dataset = numpy.loadtxt('https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv', delimiter=",")

# split into input (X) and output (Y) variables, splitting csv data
X = dataset[:, 0:8]
Y = dataset[:, 8]

x_train, x_validation, y_train, y_validation = train_test_split(X, Y, test_size=0.20, random_state=5)

型号

#create the input layer
input_layer = Input(shape=(8,))

A2 = Dense(8, activation='relu')(input_layer)
A3 = Dense(30, activation='relu')(A2)

B2 = Dense(40, activation='relu')(input_layer)
B3 = Dense(30, activation='relu')(B2)

C2 = Dense(50, activation='relu')(input_layer)
C3 = Dense(5, activation='relu')(C2)


merged = tf.keras.layers.concatenate([A3,B3,C3])
final_out = Dense(1, activation='sigmoid')(merged)

final_model = Model(inputs=[input_layer], outputs=final_out)
tf.keras.utils.plot_model(final_model)

训练

final_model.compile(loss="binary_crossentropy",
              optimizer="adam", metrics=['accuracy'])

# call the function to fit to the data (training the network)
final_model.fit(x_train, y_train, epochs=5, batch_size=50,
          validation_data=(x_validation, y_validation))

# evaluate the model
scores = final_model.evaluate(x_validation,y_validation)
print("\n%s: %.2f%%" % (final_model.metrics_names[1], scores[1] * 100))

Epoch 1/5
13/13 [==============================] - 1s 15ms/step - loss: 0.7084 - accuracy: 0.6803 - val_loss: 0.6771 - val_accuracy: 0.6883
Epoch 2/5
13/13 [==============================] - 0s 5ms/step - loss: 0.6491 - accuracy: 0.6600 - val_loss: 0.5985 - val_accuracy: 0.6623
Epoch 3/5
13/13 [==============================] - 0s 5ms/step - loss: 0.6161 - accuracy: 0.6813 - val_loss: 0.6805 - val_accuracy: 0.6883
Epoch 4/5
13/13 [==============================] - 0s 5ms/step - loss: 0.6335 - accuracy: 0.7003 - val_loss: 0.6115 - val_accuracy: 0.6623
Epoch 5/5
13/13 [==============================] - 0s 5ms/step - loss: 0.5684 - accuracy: 0.7285 - val_loss: 0.6150 - val_accuracy: 0.6883
5/5 [==============================] - 0s 2ms/step - loss: 0.6150 - accuracy: 0.6883

accuracy: 68.83%

---

更新

根据您的评论：

让我向您解释一下我要做什么，首先我分别创建 3 个模型 DNN，然后我尝试将这些模型组合起来以获得所有特征，然后我想使用所有提取的特征进行分类，然后进行评估准确性。这就是我真正想要开发的。

• 分别创建 3 个模型 - 好的，3 个模型
• 组合它们以获得特征 - 好的，特征提取器
• 分类 - 好的，平均模型输出特征图并传递给分类器 - 换句话说，Ensembling。

---

让我们这样做。首先，分别构建三个模型。

# Define Model A 
input_layer = Input(shape=(8,))
A2 = Dense(8, activation='relu')(input_layer)
A3 = Dense(30, activation='relu')(A2)
C3 = Dense(5, activation='relu')(A3)
model_a = Model(inputs=input_layer, outputs=C3, name="ModelA")

# Define Model B 
input_layer = Input(shape=(8,))
A2 = Dense(8, activation='relu')(input_layer)
A3 = Dense(30, activation='relu')(A2)
C3 = Dense(5, activation='relu')(A3)
model_b = Model(inputs=input_layer, outputs=C3, name="ModelB")

# Define Model C
input_layer = Input(shape=(8,))
A2 = Dense(8, activation='relu')(input_layer)
A3 = Dense(30, activation='relu')(A2)
C3 = Dense(5, activation='relu')(A3)
model_c = Model(inputs=input_layer, outputs=C3, name="ModelC")

我用的参数个数一样，自己改。无论如何，这三个模型作为每个特征提取器（而不是分类器）执行。接下来，我们将通过平均它们组合它们的输出，然后将其传递给分类器。

all_three_models = [model_a, model_b, model_c]
all_three_models_input = Input(shape=all_three_models[0].input_shape[1:])


models_output = [model(all_three_models_input) for model in all_three_models]
Avg           = tf.keras.layers.average(models_output, name="Average")
final_out     = Dense(1, activation='sigmoid')(Avg)
final_model   = Model(inputs=all_three_models_input, outputs=final_out, name='Ensemble')

tf.keras.utils.plot_model(final_model, expand_nested=True)

现在，您可以训练模型并在测试集上对其进行评估。希望这会有所帮助。

---

更多信息。

(1)。您可以添加种子。

from tensorflow.keras.models import Model
from sklearn.model_selection import train_test_split
import tensorflow as tf 
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from sklearn.model_selection import train_test_split
import os, numpy

# random seed for reproducibility
numpy.random.seed(101)
tf.random.set_seed(101)
os.environ['TF_CUDNN_DETERMINISTIC'] = '1'

dataset = .. your data 

# split into input (X) and output (Y) variables, splitting csv data
X = dataset[:, 0:8]
Y = dataset[:, 8]
x_train, x_validation, y_train, y_validation = train_test_split(X, Y,
                                                                
                                            test_size=0.20, random_state=101)

(2)。尝试使用 SGD 优化器。另外，使用ModelCheckpoint 回调来保存最高的validation accuracy。

final_model.compile(loss="binary_crossentropy",
              optimizer="sgd", metrics=['accuracy'])

model_save = tf.keras.callbacks.ModelCheckpoint(
                'merge_best.h5',
                monitor="val_accuracy",
                verbose=0,
                save_best_only=True,
                save_weights_only=True,
                mode="max",
                save_freq="epoch"
            )

# call the function to fit to the data (training the network)
final_model.fit(x_train, y_train, epochs=1000, batch_size=256, callbacks=[model_save],
          validation_data=(x_validation, y_validation))

在测试集上进行评估。

# evaluate the model
final_model.load_weights('merge_best.h5')
scores = final_model.evaluate(x_validation,y_validation)
print("\n%s: %.2f%%" % (final_model.metrics_names[1], scores[1] * 100))

5/5 [==============================] - 0s 4ms/step - loss: 0.6543 - accuracy: 0.7662

accuracy: 76.62%