mnist-keras

发表于 | 阅读次数:
字数统计: 349 | 阅读时长 ≈ 1

keras 训练卷积神经网络：

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
import numpy as np
from keras.datasets import mnist

# 引入卷积模块
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D

# 读入数据
(X_train, y_train), (X_test, y_test) = mnist.load_data()

print(X_train[0].shape)
print(y_train[0])

# 图像是 28 * 28 的格式 标签是0-9的数字
# 手写黑白字体变成四维张量形式 样本数量 长 宽 1
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1).astype('float32')

X_train /= 255
X_test /= 255

def tran_y(y):
	y_ohe = np.zeros(10)
	y_ohe[y] = 1
	return y_ohe

y_train_ohe = np.array([tran_y(y_train[i]) for i in range(len(y_train))])
y_test_ohe = np.array([tran_y(y_test[i]) for i in range(len(y_test))])

model = Sequential()

# 第一层卷积 64个过滤器 每个覆盖范围3*3*1 图像四周补0， relu进行非线性变化
model.add(Conv2D(filters=64, kernel_size=(3, 3), strides=(1, 1),
		  padding='same', input_shape=(28, 28, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

# 设立 dropout 层
model.add(Dropout(0.5))

model.add(Conv2D(128, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Conv2D(256, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

# 当前层节点展平
model.add(Flatten())

# 构造全连接神经网络层
model.add(Dense(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(10, activation='softmax'))

# 损失函数选择交叉熵
model.compile(loss='categorical_crossentropy',
			  optimizer='adagrad',
			  metrics=['accuracy'])

model.fit(X_train, y_train_ohe,
		  validation_data=(X_test, y_test_ohe),
		  epochs=20, batch_size=128)

scores = model.evaluate(X_test, y_test_ohe, verbose=0)