【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：
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 26, 26, 32) 320
_________________________________________________________________
conv2d_2 (Conv2D) (None, 24, 24, 64) 18496
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 12, 12, 64) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 12, 12, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 10, 10, 64) 36928
_________________________________________________________________
conv2d_4 (Conv2D) (None, 8, 8, 64) 36928
_________________________________________________________________
dropout_2 (Dropout) (None, 8, 8, 64) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 4096) 0
_________________________________________________________________
dense_1 (Dense) (None, 81) 331857
_________________________________________________________________
dropout_3 (Dropout) (None, 81) 0
_________________________________________________________________
dense_2 (Dense) (None, 10) 820
_________________________________________________________________
activation_1 (Activation) (None, 10) 0
=================================================================
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 ofollow,noindex">下載 到。