我使用以下代码（感谢这里）来运行CNN以训练MNIST图像：

from __future__ import print_functionimport kerasfrom keras.datasets import mnistfrom keras.models import Sequentialfrom keras.layers import Dense, Dropout, Flattenfrom keras.layers import Conv2D, MaxPooling2Dfrom keras import backend as Kbatch_size = 128num_classes = 10epochs = 1# input image dimensionsimg_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 /= 255x_test /= 255print('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 matricesy_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模型从MNIST中提取特征到一个数据集中，以便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，因为我只需要训练图像的特征。我找到的唯一方法是save_weights，如下所示：

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

如何从Keras模型中提取特征到数据集？

回答：

在训练或加载已存在的训练模型后，你可以创建另一个模型：

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

然后使用.predict方法返回特定层的向量，在这种情况下，每张图像将变成(128,)，这是Dense(128, …)层的输出。

你也可以使用函数式API来共同训练这些网络，并使用2个输出。按照指南，你会发现你可以将模型链接在一起，并且可以有多个输出，每个输出可能有单独的损失。这将允许你的模型学习对分类MNIST图像和你的任务都很有用的共享特征。