2019-03-28 笔记

实际训练一个简单的卷积神经网络,用来识别28x28像素图片上的数字

导入mnist的图片库,训练用图片为6万张,测试用图片为1万张

from keras.datasets import mnist
from keras.utils import to_categorical

(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
# print(train_images.shape, test_images.shape): (60000, 28, 28)
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255

#把图片表情变为张量
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

构建神经网络

from keras import layers
from keras import models

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.MaxPooling2D(2, 2)) #Using 2x2 window, stride is 2
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D(2, 2))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten()) #Flat the layers
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
print('Model summary:', model.summary())

#compile model
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

训练模型

model.fit(train_images, train_labels, epochs=4, batch_size=64)

模型精确度评估

test_loss, test_accuracy = model.evaluate(test_images, test_labels)
print('Accuracy = ', test_accuracy)

如下图所示,在没有GPU的ThinkPad笔记本上训练时长约8分钟,训练精度为99.22%,可见神经网络对这类简单的图片类型识别精确率相当高。


2019-03-28 笔记_第1张图片
result.PNG

你可能感兴趣的:(2019-03-28 笔记)