机器学习实验（八）：用特征值衰减正则化方法进行深度学习实验_3

声明：版权所有，转载请联系作者并注明出处  http://blog.csdn.net/u013719780?viewmode=contents

本文在机器学习实验（六）：用特征值衰减正则化方法进行深度学习实验_1的基础上进行第二个实验，本实验以CIFAR10数据集进行实验，相关实验代码如下。

from __future__ import print_functionfrom keras.datasets import cifar10from keras.preprocessing.image import ImageDataGeneratorfrom keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activation, Flattenfrom keras.layers.convolutional import Convolution2D, MaxPooling2Dfrom keras.optimizers import SGDfrom keras.utils import np_utils#Importing Eigenvalue Decay regularizer: #from EigenvalueDecay import EigenvalueRegularizerfrom keras.models import model_from_jsonbatch_size = 32nb_classes = 10nb_epoch = 10data_augmentation = False#True# input image dimensionsimg_rows, img_cols = 32, 32# the CIFAR10 images are RGBimg_channels = 3# the data, shuffled and split between train and test sets(X_train, y_train), (X_test, y_test) = cifar10.load_data()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 matricesY_train = np_utils.to_categorical(y_train, nb_classes)Y_test = np_utils.to_categorical(y_test, nb_classes)model = Sequential()model.add(Convolution2D(32, 3, 3, border_mode='same',                        input_shape=(img_channels, img_rows, img_cols)))model.add(Activation('relu'))model.add(Convolution2D(32, 3, 3))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Convolution2D(64, 3, 3, border_mode='same'))model.add(Activation('relu'))model.add(Convolution2D(64, 3, 3))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Flatten())model.add(Dense(512,W_regularizer=EigenvalueRegularizer(0.1))) #Applying Eigenvalue Decay with C=0.1model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(nb_classes,W_regularizer=EigenvalueRegularizer(0.1))) #Applying Eigenvalue Decay with C=0.1model.add(Activation('softmax'))# let's train the model using SGD + momentum (how original).sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)model.compile(loss='categorical_crossentropy',              optimizer=sgd,              metrics=['accuracy'])X_train = X_train.astype('float32')X_test = X_test.astype('float32')X_train /= 255X_test /= 255if not data_augmentation:    print('Not using data augmentation.')    model.fit(X_train, Y_train,              batch_size=batch_size,              nb_epoch=nb_epoch,              validation_data=(X_test, Y_test),              shuffle=True)else:    print('Using real-time data augmentation.')    # this will do preprocessing and realtime data augmentation    datagen = ImageDataGenerator(        featurewise_center=False,  # set input mean to 0 over the dataset        samplewise_center=False,  # set each sample mean to 0        featurewise_std_normalization=False,  # divide inputs by std of the dataset        samplewise_std_normalization=False,  # divide each input by its std        zca_whitening=False,  # apply ZCA whitening        rotation_range=0,  # randomly rotate images in the range (degrees, 0 to 180)        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)        horizontal_flip=True,  # randomly flip images        vertical_flip=False)  # randomly flip images    # compute quantities required for featurewise normalization    # (std, mean, and principal components if ZCA whitening is applied)    datagen.fit(X_train)    # fit the model on the batches generated by datagen.flow()    model.fit_generator(datagen.flow(X_train, Y_train,                        batch_size=batch_size),                        samples_per_epoch=X_train.shape[0],                        nb_epoch=nb_epoch,                        validation_data=(X_test, Y_test))                                                model.save_weights('my_model_weights.h5')print('model weights trained with Eigenvalue decay saved')#**********************************  tricking Keras ;-)  ***********************************************************#Creating a new model, similar but without Eigenvalue Decay, to use with the weights adjusted with Eigenvalue Decay: #*******************************************************************************************************************model = Sequential()model.add(Convolution2D(32, 3, 3, border_mode='same',                        input_shape=(img_channels, img_rows, img_cols)))model.add(Activation('relu'))model.add(Convolution2D(32, 3, 3))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Convolution2D(64, 3, 3, border_mode='same'))model.add(Activation('relu'))model.add(Convolution2D(64, 3, 3))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Flatten())model.add(Dense(512))model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(nb_classes))model.add(Activation('softmax'))json_string = model.to_json()open('my_model_struct.json', 'w').write(json_string)print('model structure without Eigenvalue Decay saved')model = model_from_json(open('my_model_struct.json').read())sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)model.compile(loss='categorical_crossentropy',              optimizer=sgd,              metrics=['accuracy'])#Loading the weights trained with Eigenvalue Decay:model.load_weights('my_model_weights.h5')#Showing the same results as before: score = model.evaluate(X_test, Y_test, verbose=0)print('Test score of saved model:', score[0])print('Test accuracy of saved model:', score[1])

X_train shape: (50000, 3, 32, 32)50000 train samples10000 test samplesNot using data augmentation.Train on 50000 samples, validate on 10000 samplesEpoch 1/1050000/50000 [==============================] - 399s - loss: 2.0288 - acc: 0.3536 - val_loss: 1.3774 - val_acc: 0.5010Epoch 2/1050000/50000 [==============================] - 440s - loss: 1.6359 - acc: 0.5179 - val_loss: 1.1484 - val_acc: 0.6011Epoch 3/1050000/50000 [==============================] - 408s - loss: 1.4912 - acc: 0.5817 - val_loss: 1.1446 - val_acc: 0.6026Epoch 4/1050000/50000 [==============================] - 407s - loss: 1.3987 - acc: 0.6219 - val_loss: 0.9291 - val_acc: 0.6796Epoch 5/1050000/50000 [==============================] - 445s - loss: 1.3316 - acc: 0.6518 - val_loss: 0.8456 - val_acc: 0.7160Epoch 6/1050000/50000 [==============================] - 460s - loss: 1.2835 - acc: 0.6707 - val_loss: 0.8413 - val_acc: 0.7115Epoch 7/1050000/50000 [==============================] - 409s - loss: 1.2471 - acc: 0.6872 - val_loss: 0.7789 - val_acc: 0.7309Epoch 8/1050000/50000 [==============================] - 390s - loss: 1.2094 - acc: 0.7040 - val_loss: 0.7420 - val_acc: 0.7452Epoch 9/1050000/50000 [==============================] - 394s - loss: 1.1906 - acc: 0.7141 - val_loss: 0.7527 - val_acc: 0.7402Epoch 10/1050000/50000 [==============================] - 405s - loss: 1.1706 - acc: 0.7243 - val_loss: 0.7497 - val_acc: 0.7524model weights trained with Eigenvalue decay savedmodel structure without Eigenvalue Decay savedTest score of saved model: 0.749746108055Test accuracy of saved model: 0.7524