Handwritten Digit Recognition using Python
使用Python进行手写数字识别
作者：科画宇
What is Handwritten Digit Recognition?什么是手写数字识别?
The handwritten digit recognition is the ability of computers to recognize human handwritten digits.
手写体数字识别是指计算机识别人类手写体数字的能力。
It is a hard task for the machine becau handwritten digits are not perfect and can be made with many different flavors.
这对机器来说是一项艰巨的任务，因为手写数字并不完美，可以做出许
acome
多不同的口味。
The handwritten digit recognition is the solution to this problem which us the image of a digit and recognizes the digit prent in the image.手写体数字识别就是利用一个数字的图像，对图像中的数字进行识别，
从而解决这一问题。日语翻译收费标准
the shadowAbout the Python AI Project
关于这个Python AI项目
孩子成绩不好怎么办In this article, we are going to implement a handwritten digit recognition app using the MNIST datat.
在本文中，我们将使用MNIST数据集实现一个手写数字识别应用程序。We will be using a special type of deep neural network that is Convolutional Neural Networks.
我们将使用一种特殊类型的深度神经网络，卷积神经网络。
In the end, we are going to build a GUI in which you can draw the digit and recognize it straight away.
dutycycle>globalmarket最后，我们将构建一个GUI，您可以在其中绘制数字并直接识别它。
Prerequisites
预备知识love cat
The interesting Python project requires you to have basic knowledge of Python programming, deep learning with Keras library and the Tkinter library for building GUI.
这个有趣的Python项目要求您具备Python编程的基本知识，以及使用Keras库进行的深度学习和用于构建GUI的Tkinter库。
l是什么意思Install the necessary libraries for this project using this command:
使用以下命令给这个项目安装必要的库:
The MNIST datat
MNIST数据集
This is probably one of the most popular datats among machine learning and deep learning enthusiasts.
drone这可能是机器学习和深度学习爱好者最喜欢的数据集之一。
The MNIST datat contains 60,000 training images of handwritten digits from zero to nine and 10,000 images for testing.
MNIST数据集包含从0到9的手写数字的60000张训练图像，以及10000张用于测试的图像。
So, the MNIST datat has 10 different class. The handwritten digits images are reprented as a 28×28 matrix where each cell contains grayscale pixel value.
植树节英文
因此，MNIST数据集有10个不同的类。手写数字图像用28×28矩阵表示，其中每个单元都包含灰度像素值。
