python之从 keras 模型中提取特征到数据集中

我使用以下代码(由 here 提供)运行 CNN 来训练 MNIST 图像:

from __future__ import print_function 
import keras 
from keras.datasets import mnist 
from keras.models import Sequential 
from keras.layers import Dense, Dropout, Flatten 
from keras.layers import Conv2D, MaxPooling2D 
from keras import backend as K 
 
batch_size = 128 
num_classes = 10 
epochs = 1 
 
# input image dimensions 
img_rows, img_cols = 28, 28 
 
# the data, split between train and test sets 
(x_train, y_train), (x_test, y_test) = mnist.load_data() 
 
if K.image_data_format() == 'channels_first': 
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols) 
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols) 
    input_shape = (1, img_rows, img_cols) 
else: 
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1) 
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1) 
    input_shape = (img_rows, img_cols, 1) 
 
x_train = x_train.astype('float32') 
x_test = x_test.astype('float32') 
x_train /= 255 
x_test /= 255 
print('x_train shape:', x_train.shape) 
print(x_train.shape[0], 'train samples') 
print(x_test.shape[0], 'test samples') 
 
# convert class vectors to binary class matrices 
y_train = keras.utils.to_categorical(y_train, num_classes) 
y_test = keras.utils.to_categorical(y_test, num_classes) 
 
model = Sequential() 
model.add(Conv2D(32, kernel_size=(3, 3), 
                 activation='relu', 
                 input_shape=input_shape)) 
model.add(Conv2D(64, (3, 3), activation='relu')) 
model.add(MaxPooling2D(pool_size=(2, 2))) 
model.add(Dropout(0.25)) 
model.add(Flatten()) 
model.add(Dense(128, activation='relu')) 
model.add(Dropout(0.5)) 
model.add(Dense(num_classes, activation='softmax')) 
 
model.compile(loss=keras.losses.categorical_crossentropy, 
              optimizer=keras.optimizers.Adadelta(), 
              metrics=['accuracy']) 
model.fit(x_train, y_train, 
          batch_size=batch_size, 
          epochs=epochs, 
          verbose=1, 
          validation_data=(x_test, y_test)) 
 
print(model.save_weights('file.txt')) # <<<<<---- 
 
score = model.evaluate(x_test, y_test, verbose=0) 
print('Test loss:', score[0]) 
print('Test accuracy:', score[1]) 

我的目标是使用 CNN 模型将 MNIST 特征提取到数据集中，我可以将其用作另一个分类器的输入。在这个例子中，我不关心分类操作，因为我需要的只是训练图像的特征。我找到的唯一方法是 save_weights as:

print(model.save_weights('file.txt'))

如何从 keras 模型中提取特征到数据集中？

请您参考如下方法:

在训练或加载现有训练模型后，您可以创建另一个模型:

extract = Model(model.inputs, model.layers[-3].output) # Dense(128,...) 
features = extract.predict(data) 

并使用 .predict 方法从特定层返回向量，在这种情况下，每个图像都将变为 (128,)，Dense(128, ...) 层的输出.

您还可以使用 functional API 使用 2 个输出联合训练这些网络.按照指南进行操作，您会发现可以将模型链接在一起，并有多个输出，每个输出都可能有单独的损失。这将允许您的模型学习对同时对 MNIST 图像和您的任务进行分类有用的共享特征。