说明:该程序是一个包含两个隐藏层的神经网络。演示如何加载一个保存好的模型。
数据集:MNIST
1.加载keras模块
from __future__ import print_function
#Python提供了__future__模块,把下一个新版本的特性导入到当前版本,于是我们就可以在当前版本中测试一些新版本的特性。
import numpy as np
np.random.seed(1337) # for reproducibility
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense,Dropout,Activation
from keras.optimizers import SGD,Adam,RMSprop
from keras.utils import np_utils
需要加载load_model
from keras.models import load_model
- 变量初始化
batch_size = 128
nb_classes = 10
nb_epoch = 20
- 准备数据
# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
#转换类标号
# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
- 建立模型
#在现有的文件中加载模型
model=load_model('mnist-mpl.h5')
#打印模型
model.summary()
- 训练与评估
#编译模型
model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(),
metrics=['accuracy'])
- 模型评估
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])