多层感知机、卷积神经网络、深度卷积神经网络实现图片的二元分类

应用范围：
1：人脸部照片性别识别
2：产品线上产品优劣识别
3：医疗照片是否患病识别

# 多层感应器神经网络模型
# 0. 调用要使用的包
from keras.utils import np_utils
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Activation
width = 28
height = 28
# 1. 生成数据集
# 调用训练集和测试集
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, width*height).astype('float32') / 255.0   #正则化  
x_test = x_test.reshape(10000, width*height).astype('float32') / 255.0
# 分离训练集和验证集
x_val = x_train[50000:]
y_val = y_train[50000:]
x_train = x_train[:50000]
y_train = y_train[:50000]
# 数据集预处理：奇数转换为 1，偶数转换为 0
y_train = y_train % 2
y_val = y_val % 2
y_test = y_test % 2
# 2. 搭建模型
model = Sequential()
model.add(Dense(256, input_dim=width*height, activation='relu'))
model.add(Dense(256, activation='relu'))
model.add(Dense(256, activation='relu'))
model.add(Dense(128, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# 3. 设置模型训练过程
model.compile(loss='binary_crossentropy', optimizer='sgd', metrics=['accuracy'])
# 4. 训练模型
hist = model.fit(x_train, y_train, epochs=50, batch_size=64, validation_data=(x_val, y_val))

# 5. 查看训练过程
%matplotlib inline
import matplotlib.pyplot as plt
fig, loss_ax = plt.subplots()
acc_ax = loss_ax.twinx()
loss_ax.plot(hist.history['loss'], 'b', label='train loss')
loss_ax.plot(hist.history['val_loss'], 'r', label='val loss')
loss_ax.set_ylim([0.0, 1.5])
acc_ax.plot(hist.history['accuracy'], 'black', label='train acc')
acc_ax.plot(hist.history['val_accuracy'], 'g', label='val acc')
acc_ax.set_ylim([0.0, 1.5])
loss_ax.set_xlabel('epoch')
loss_ax.set_ylabel('loss')
acc_ax.set_ylabel('accuracy')
loss_ax.legend(loc='upper left')
acc_ax.legend(loc='upper right')
plt.show()


# 6. 评价模型
loss_and_metrics = model.evaluate(x_test, y_test, batch_size=32)
print('## evaluation loss and_metrics ##')
print(loss_and_metrics)
# 7. 调用模型
yhat_test = model.predict(x_test, batch_size=32)

%matplotlib inline
import matplotlib.pyplot as plt
plt_row =6
plt_col = 6
plt.rcParams["figure.figsize"] = (10,10)
f, axarr = plt.subplots(plt_row, plt_col)
for i in range(plt_row * plt_col):
    sub_plt = axarr[i//plt_row, i%plt_col]   #排列成一个方阵 6*6 
    sub_plt.axis('off')     #不要坐标刻度
    sub_plt.imshow(x_test[i].reshape(width, height))  #一副图像
   


    sub_plt_title = 'R: '   #实际值
    if y_test[i] >= 0.5 :                #数据集预处理：奇数转换为 1，偶数转换为 0    
        sub_plt_title += 'odd '  #奇数
    else:
        sub_plt_title += 'even'  #偶数
    sub_plt_title += ' P: '
    if yhat_test[i] >= 0.5 :
        sub_plt_title += 'odd '
    else:
        sub_plt_title += 'even '
    sub_plt.set_title(sub_plt_title)
plt.show()





#卷积神经网络模型
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(width, height, 1)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dense(1, activation='sigmoid'))


#深度卷积神经网络模型
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(width, height, 1)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
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(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))