Keras卷积神经网络识别手写数字

一、进行数据预处理

步骤1：导入所需模块

import tensorflow as tf
import tensorflow.keras
from tensorflow.keras.datasets import mnist
import numpy as np
import pandas as pd
from tensorflow.keras.utils import to_categorical
np.random.seed(10)

步骤2：读取MNIST数据

(x_train, y_train), \
(x_test, y_test) = mnist.load_data()

步骤3：将features（数字图像特征值）转换为四维矩阵
将features（数字图像特征值）以reshape转换为600002828*1的四维矩阵

x_train4d=x_train.reshape(x_train.shape[0],28,28,1).astype('float32')
x_test4d=x_test.reshape(x_test.shape[0],28,28,1).astype('float32')

步骤4：将features（数字图像特征值）标准化

x_train4d_normalize = x_train4d/255
x_test4d_normalize = x_test4d/255

步骤5：label（数字真实的值）以One-Hot Encoding进行转换

y_trainonehot =tf.keras.utils. to_categorical(y_train)
y_testonehot = tf.keras.utils.to_categorical(y_test)

二、 建立模型

1.导入所需模块

from tensorflow.keras.models impor