TensorFlow2.0 卷积神经网络MNIST实战

综述

使用 TensorFlow 2.0 框架搭建卷积神经网络，进行手写字的识别。完整代码可见我的GitHub。

代码与结果

导入库

import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import sklearn
import os
import sys
import time
from tensorflow import keras

print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__ + "的版本为：" + module.__version__)

导入数据

minst = keras.datasets.mnist

数据拆分

img_rows, img_cols = 28, 28

(x_train, y_train), (x_test, y_test) = minst.load_data()

if keras.backend.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)
    
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

数据规范化

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')

x_train = x_train / 255
x_test = x_test / 255

x_train.shape

独热编码

y_train_onehot = tf.keras.utils.to_categorical(y_train)
y_test_onehot = tf.keras.utils.to_categorical(y_test)

搭建卷积神经网络模型

model = tf.keras.Sequential()

model.add(tf.keras.layers.Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add(tf.keras.layers.Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Dense(10, activation='softmax'))

model.summary()

设置优化器、损失函数

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

模型训练

history = model.fit(x_train, y_train_onehot, batch_size = 256, epochs = 10, verbose=1, validation_data = (x_test, y_test_onehot))

结果检测

score = model.evaluate(x_test, y_test_onehot, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])