1 # -*- coding: utf-8 -*- 2 """ 3 Created on Sun Jan 20 11:25:29 2019 4 5 @author: zhen 6 """ 7 8 import numpy as np 9 from keras.datasets import mnist 10 from keras.models import Sequential 11 from keras.layers import Dense 12 from keras.layers import Dropout 13 from keras.layers import Flatten 14 from keras.layers.convolutional import Conv2D 15 from keras.layers.convolutional import MaxPooling2D 16 17 # 加载数据 18 (x_train, y_train), (x_test, y_test) = mnist.load_data("../test_data_home") 19 # 转化训练数据为四维张量形式 20 x_train = x_train.reshape(x_train.shape[0], 28, 28, 1).astype("float32") 21 x_test = x_test.reshape(x_test.shape[0], 28, 28, 1).astype("float32") 22 # 归一化 23 x_train /= 255 24 x_test /= 255 25 26 #转化为one hot 编码 27 def to_one_hot(y): 28 y_one_hot = np.zeros(10) # 生成全零向量 29 y_one_hot[y] = 1 30 return y_one_hot 31 32 # 重置标签 33 y_train_one_hot = np.array([to_one_hot(y_train[i]) for i in range(len(y_train))]) 34 y_test_one_hot = np.array([to_one_hot(y_test[i]) for i in range(len(y_test))]) 35 # 搭建卷积神经网络 36 model = Sequential() 37 model.add(Conv2D(filters=32, kernel_size=(3, 3), strides=(1, 1), padding='same', input_shape=(28, 28, 1), 38 activation='relu')) 39 # 添加最大池化层 40 model.add(MaxPooling2D(pool_size=(2, 2))) 41 # 添加Dropout层 42 model.add(Dropout(0.2)) 43 # 构建深度网络 44 model.add(Conv2D(64, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu')) 45 model.add(MaxPooling2D(pool_size=(2, 2))) 46 model.add(Dropout(0.2)) 47 model.add(Conv2D(128, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu')) 48 model.add(MaxPooling2D(pool_size=(2, 2))) 49 model.add(Dropout(0.2)) 50 # 展开 51 model.add(Flatten()) 52 # 构造全连接层 53 model.add(Dense(128, activation='relu')) 54 model.add(Dense(64, activation='relu')) 55 model.add(Dense(32, activation='relu')) 56 model.add(Dense(10, activation='softmax')) 57 # 定义损失函数 58 model.compile(loss='categorical_crossentropy', optimizer='adagrad', 59 metrics=['accuracy']) 60 # 训练 61 model.fit(x_train, y_train_one_hot, validation_data=(x_test, y_test_one_hot), 62 epochs=2, batch_size=128) 63 # 评估 64 # verbose : 0表示不显示数据,1表示显示进度 65 scores = model.evaluate(x_test, y_test_one_hot, verbose=0) 66 print(scores)
结果：
