【Python】keras卷積神經網路識別mnist

卷積神經網路的結構我隨意設了一個。

結構大概是下面這個樣子：

 

程式碼如下：

import numpy as np
from keras.preprocessing import image
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Activation
from keras.layers import Conv2D, MaxPooling2D

# 從資料夾影象與標籤檔案載入資料
def create_x(filenum, file_dir):
    train_x = []
    for i in range(filenum):
        img = image.load_img(file_dir + str(i) + ".bmp", target_size=(28, 28))
        img = img.convert('L')
        x = image.img_to_array(img)
        train_x.append(x)
    train_x = np.array(train_x)
    train_x = train_x.astype('float32')
    train_x /= 255
    return train_x


def create_y(classes, filename):
    train_y = []
    file = open(filename, "r")
    for line in file.readlines():
        tmp = []
        for j in range(classes):
            if j == int(line):
                tmp.append(1)
            else:
                tmp.append(0)
        train_y.append(tmp)
    file.close()
    train_y = np.array(train_y).astype('float32')
    return train_y

classes = 10
X_train = create_x(55000, './train/')
X_test = create_x(10000, './test/')

Y_train = create_y(classes, 'train.txt')
Y_test = create_y(classes, 'test.txt')

# 從網路下載的資料集直接解析資料
'''
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
X_train, Y_train = mnist.train.images, mnist.train.labels
X_test, Y_test = mnist.test.images, mnist.test.labels
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
'''
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(Conv2D(64, (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(Dropout(0.25))

model.add(Flatten())
model.add(Dense(81, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10))
model.add(Activation('softmax'))
model.summary()

model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
history = model.fit(X_train, Y_train, batch_size=500, epochs=10, verbose=1, validation_data=(X_test, Y_test))
score = model.evaluate(X_test, Y_test, verbose=0)

test_result = model.predict(X_test)
result = np.argmax(test_result, axis=1)

print(result)
print('Test score:', score[0])
print('Test accuracy:', score[1])

最終在測試集上識別率在99%左右。

相關測試資料可以在這裡下載到。