tensorflow入门学习(4)—— 实现简单的Neural Network模型

通过手写数字集的样例，来熟悉使用tensorflow搭建神经网络模型，进行识别
Reference: https://github.com/aymericdamien/TensorFlow-Examples/

导入数据

这里导入官方的数据集
The MNIST database of handwritten digits, available from this page, has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from NIST. The digits have been size-normalized and centered in a fixed-size image.

training set images (9912422 bytes)
training set labels (28881 bytes)
test set images (1648877 bytes)
test set labels (4542 bytes)

构建模型

1.通过tf.placeholder创建X，Y表示训练集特征和label两个空的tensor
（上面是一些参数下面会提到）

2.创建每层的weights，biases参数

3.创建神经网络的模型
Input(784)→HiddenLayer1(256)