多层感知机、卷积神经网络、深度卷积神经网络实现图像的多元识别

应用场景:
1: 实现植物的分类
2：各种有区别度的分类
3：台风的类型
4：细菌的种类

#多层感应器神经网络模型
# 0. 调用要使用的包
import numpy as np31
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
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：独热编码
y_train = np_utils.to_categorical(y_train)
y_val = np_utils.to_categorical(y_val)
y_test = np_utils.to_categorical(y_test)
# 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(10, activation='softmax'))
# 3. 设置模型训练过程
model.compile(loss='categorical_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_test, y_test))

# 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])
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([0.8, 1.2])
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 = 8
plt_col = 8
plt.rcParams["figure.figsize"] = (12,12)
f, axarr = plt.subplots(plt_row, plt_col)
cnt = 0
i = 0
while cnt < (plt_row*plt_col):
    if np.argmax(y_test[i]) == np.argmax(yhat_test[i]):
        i += 1
        continue
    sub_plt = axarr[cnt//plt_row, cnt%plt_col]
    sub_plt.axis('off')
    sub_plt.imshow(x_test[i].reshape(width, height))
    sub_plt_title = 'R: ' + str(np.argmax(y_test[i])) + 'P: ' + str(np.argmax(yhat_test[i]))
    sub_plt.set_title(sub_plt_title)
    i += 1
    cnt += 1
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(10, activation='softmax'))


#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(10, activation='softmax'))