keras CNN例子

前言

本文介绍的是keras的CNN的例子，代码的具体解释都在下面，源码是b站up主莫烦python的

---

1.代码

代码如下（示例）：

import numpy as np
np.random.seed(1377)
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Activation, Convolution2D, MaxPooling2D, Flatten
from keras.optimizers import Adam

#dowmload the mnist to the path
(X_train, y_train), (X_test, y_test) = mnist.load_data()

#data pre-processing
X_train = X_train.reshape(-1, 1, 28, 28)#-1是样本数量，没有固定拿来随便代替 1是图片是灰度的 RGB就是3
X_test = X_test.reshape(-1, 1, 28, 28)
y_train = np_utils.to_categorical(y_train, num_classes=10)
y_test = np_utils.to_categorical(y_test, num_classes=10)

#Another way to build your CNN
model = Sequential()

#Conv layer 1 output shape(32, 28, 28)
model.add(Convolution2D(
    nb_filter=32,#滤波器有32个,每个滤波器都会扫过这个图片，会得到另外一整张图片，所以之后得到的告诉是32层
    nb_row=5,#滤波器的行
    nb_col=5,#~列
    border_mode='same',#padding method滤波器在过滤时候用什么方式 same就是长和宽不变
    input_shape=(1,#channels
                 28,28)#height&width
))
model.add(Activation('relu'))

#Pooling layer 1 (max pooling) output shape(32, 14, 14)
model.add(MaxPooling2D(
    pool_size=(2,2),
    strides=(2,2),
    border_mode='same' #padding method
))

#Conv layer 2 output shape(64,14,14)
model.add(Convolution2D(64, 5, 5, border_mode='same'))
model.add(Activation('relu'))

#Pooling layer 2 (max pooling) output shape(64, 7, 7)
model.add(MaxPooling2D(pool_size=(2,2), border_mode='same'))

#Fully connected layer 1 input shape (64 * 7 * 7)=(3136), output shape(1024)
#抹平就是为了可以把这一个一个点全连接成一个层.
model.add(Flatten())#Flatten层用来将输入“压平”，即把多维的输入一维化，常用在从卷积层到全连接层的过渡。Flatten不影响batch的大小。
model.add(Dense(1024))#1024是自己定义的神经元的个数，可以设置其他的
model.add(Activation('relu'))

#Fully connected layer 2 to shape (10) for 10 classes
model.add(Dense(10))#输出 10 个 unit, 用 softmax 作为分类。
model.add(Activation('softmax'))

#Another way to define your optomizer
adam = Adam(lr=1e-4)

#We add metrics to get more results you want to see
model.compile(optimizer=adam,
              loss='categorical_crossentropy',#分类交叉熵函数
              metrics=['accuracy'])

print('Training--------')
#Another way to train the model
model.fit(X_train, y_train, nb_epoch=1, batch_size=32,)

print('\nTesting--------')

#Evaluate the model with the metrics we defined earlier
loss, accuracy = model.evaluate(X_test, y_test)

print('\ntest loss:', loss)
print('\ntest accuracy:', accuracy)

2.运行结果

Training--------
Epoch 1/1
60000/60000 [==============================] - 53s 889us/step - loss: 0.2842 - accuracy: 0.9179
Testing--------
10000/10000 [==============================] - 2s 212us/step
test loss: 0.10877728501232341

test accuracy: 0.9679999947547913

---

总结

感动，发现keras真的挺好用的，上手也还可以，再刷两节课就去看我的骨龄预测了。。。。。。。