Tensorflow2.x框架-MNIST数据集

MNIST数据集
博主微信公众号（左）、Python+智能大数据+AI学习交流群（右）：欢迎关注和加群，大家一起学习交流，共同进步！
<img alt="" height="129" src="https://beijingoptbbs.oss-cn-beijing.aliyuncs.com/cs/5606289-b7c5ef7f266af46806ec9ded631e32ca.png" width="129"><img alt="" height="266" src="https://beijingoptbbs.oss-cn-beijing.aliyuncs.com/cs/5606289-5d1832dd37e5b2075a75a99d807efc9c.jpg" width="200">
目录
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E6%91%98%E8%A6%81">摘要</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E4%B8%80%E3%80%81%E5%AF%BC%E5%85%A5%E6%A8%A1%E5%9D%97">一、导入模块</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E4%BA%8C%E3%80%81%E5%AF%BC%E5%85%A5%20MNIST%C2%A0%E6%95%B0%E6%8D%AE%E9%9B%86">二、导入 MNIST 数据集</a>
<p id="%E4%B8%89%E3%80%81%E4%BD%9C%E4%B8%BA%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%EF%BC%8C%E8%BE%93%E5%85%A5%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E6%97%B6%EF%BC%8C%E5%B0%86%E6%95%B0%E6%8D%AE%E6%8B%89%E4%BC%B8%E4%B8%BA%E4%B8%80%E7%BB%B4%E6%95%B0%E7%BB%84-toc" style="margin-left:80px;"><a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E4%B8%89%E3%80%81%E4%BD%9C%E4%B8%BA%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%EF%BC%8C%E8%BE%93%E5%85%A5%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E6%97%B6%EF%BC%8C%E5%B0%86%E6%95%B0%E6%8D%AE%E6%8B%89%E4%BC%B8%E4%B8%BA%E4%B8%80%E7%BB%B4%E6%95%B0%E7%BB%84">三、作为输入特征，输入神经网络时，将数据拉伸为一维数组</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E5%9B%9B%E3%80%81%E5%8F%AF%E8%A7%86%E5%8C%96%E8%AE%AD%E7%BB%83%E9%9B%86%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%E7%9A%84%E7%AC%AC%E4%B8%80%E4%B8%AA%E5%85%83%E7%B4%A0">四、可视化训练集输入特征的第一个元素</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E4%BA%94%E3%80%81%E6%89%93%E5%8D%B0%E5%87%BA%E8%AE%AD%E7%BB%83%E9%9B%86%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%E7%9A%84%E7%AC%AC%E4%B8%80%E4%B8%AA%E5%85%83%E7%B4%A0">五、打印出训练集输入特征的第一个元素</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E5%85%AD%E3%80%81%E6%89%93%E5%8D%B0%E5%87%BA%E8%AE%AD%E7%BB%83%E9%9B%86%E6%A0%87%E7%AD%BE%E7%9A%84%E7%AC%AC%E4%B8%80%E4%B8%AA%E5%85%83%E7%B4%A0">六、打印出训练集标签的第一个元素</a>
<p id="%E4%B8%83%E3%80%81%E6%89%93%E5%8D%B0%E5%87%BA%E8%AE%AD%E7%BB%83%E9%9B%86%EF%BC%88%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%E3%80%81%E6%A0%87%E7%AD%BE%EF%BC%89%E3%80%81%E6%B5%8B%E8%AF%95%E9%9B%86%EF%BC%88%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%E3%80%81%E6%A0%87%E7%AD%BE%EF%BC%89%E7%9A%84%E5%BD%A2%E7%8A%B6-toc" style="margin-left:80px;"><a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E4%B8%83%E3%80%81%E6%89%93%E5%8D%B0%E5%87%BA%E8%AE%AD%E7%BB%83%E9%9B%86%EF%BC%88%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%E3%80%81%E6%A0%87%E7%AD%BE%EF%BC%89%E3%80%81%E6%B5%8B%E8%AF%95%E9%9B%86%EF%BC%88%E8%BE%93%E5%85%A5%E7%89%B9%E5%BE%81%E3%80%81%E6%A0%87%E7%AD%BE%EF%BC%89%E7%9A%84%E5%BD%A2%E7%8A%B6">七、打印出训练集（输入特征、标签）、测试集（输入特征、标签）的形状</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E5%85%AB%E3%80%81%E5%AE%8C%E6%88%90%E4%BB%A3%E7%A0%81">八、完整代码</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E4%B9%9D%E3%80%81Sequential%28%29%C2%A0%E5%AE%9E%E7%8E%B0%E6%89%8B%E5%86%99%E6%95%B0%E5%AD%97%E8%AF%86%E5%88%AB">九、Sequential() 实现手写数字识别</a>
<a href="https://blog.csdn.net/weixin_38477351/article/details/115290903#%E5%8D%81%E3%80%81Class%28%29%C2%A0%E5%AE%9E%E7%8E%B0%E6%89%8B%E5%86%99%E6%95%B0%E5%AD%97%E8%AF%86%E5%88%AB">十、Class() 实现手写数字识别</a>
<hr id="hr-toc">
<h3 id="%E6%91%98%E8%A6%81">摘要</h3>
MNIST 数据集：
 提供 6w 张 28*28 像素点的 0~9 手写数字图片和标签，用于训练。