这是 codelab 的支持代码 “Tensorflow和深度学习 – 没有博士学位”
演示文稿在这里解释底层概念，您将在上一张幻灯片中找到 codelab 指令。 不要忘记在演示文稿中打开演讲者笔记，很多解释都在那里。
该实验需要2.5小时，通过设计和优化神经网络来识别手写数字，从最简单的可能解决方案到99％以上的识别精度。 它涵盖了密集和卷积网络，以及诸如学习速率衰减和丢失等技术。
安装说明在这里。 简短的版本是：安装Python3，然后 pip3 安装 tensorflow 和 matplotlib。
这个回购中最先进的先进神经网络在MNIST数据集上达到了99.5％的准确率（世界最好的是99.7％）并且使用批量归一化。
项目地址：https://github.com/martin-gorner/tensorflow-mnist-tutorial
PPT 地址：https://docs.google.com/presentation/d/1TVixw6ItiZ8igjp6U17tcgoFrLSaHWQmMOwjlgQY9co/pub?slide=id.g110257a6da_0_13
在线教程地址：https://codelabs.developers.google.com/codelabs/cloud-tensorflow-mnist/
This is support code for the codelab “Tensorflow and deep learning – without a PhD”
The presentation explaining the underlying concepts is here and you will find codelab instructions to follow on its last slide. Do not forget to open the speaker notes in the presentation, a lot of the explanations are there.
The lab takes 2.5 hours and takes you through the design and optimisation of a neural network for recognising handwritten digits, from the simplest possible solution all the way to a recognition accuracy above 99%. It covers dense and convolutional networks, as well as techniques such as learning rate decay and dropout.
Installation instructions here. The short version is: install Python3, then pip3 install tensorflow and matplotlib.
The most advanced advanced neural network in this repo achieves 99.5% accuracy on the MNIST dataset (world best is 99.7%) and uses batch normalization.
